© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 31-GEMMASCOPE-RES-16K
    11. 10645
    Prev
    Next
    INDEX
    Explanations

    annotations and elements related to Java persistence frameworks and entity definitions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Java annotation decorators and their associated parameters.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou

    Java annotations and decorators, particularly those used in dependency injection and ORM frameworks.

    oai_token-act-pair · claude-4-5-sonnetTriggered by @jyhe0408

    Java source annotations and their parameterized metadata (framework/ORM configuration declarations).

    oai_token-act-pair · gpt-5Triggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.47
    MethodManager
    -0.44
    BeginInit
    -0.40
    TypedDataSet
    -0.39
    WithIOException
    -0.39
    AutoScaleMode
    -0.37
     frattempo
    -0.36
    uduk
    -0.36
    ibouti
    -0.36
     EconPapers
    -0.35
    POSITIVE LOGITS
     value
    0.51
    value
    0.50
     fisuras
    0.43
     Roskov
    0.43
     PopupWindow
    0.42
    AccessLevel
    0.42
     TestBed
    0.41
     valore
    0.41
    Subviews
    0.41
     peixe
    0.40
    Activations Density 0.078%

    No Known Activations