© 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-2-2B
    7. Residual Stream - 16k
    9. 1-GEMMASCOPE-RES-16K
    11. 10295
    Prev
    Next
    INDEX
    Explanations

    code-related structures and constructs, particularly those pertaining to Java repositories and their configurations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SourceChecksum
    -0.66
     съм
    -0.49
     Gedächt
    -0.49
    styleable
    -0.48
    RLock
    -0.47
    ProcessEvent
    -0.47
     ocur
    -0.46
     Signalez
    -0.44
    Спољашње
    -0.43
    mergeFrom
    -0.43
    POSITIVE LOGITS
    AndEndTag
    0.85
    DockStyle
    0.76
    KommentareTeilen
    0.72
    NewUrlParser
    0.67
     noqa
    0.67
    Rüyada
    0.66
    rungsseite
    0.66
     Normdatei
    0.66
    Hentet
    0.65
    tableFuture
    0.59
    Activations Density 0.318%

    No Known Activations