© 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. 15587
    Prev
    Next
    INDEX
    Explanations

    keywords related to access modifiers and data types in programming

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

    access modifiers and visibility keywords in code declarations.

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

    the keyword "private" in variable declarations within code, especially when followed by type declarations.

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

    object-oriented code declarations—especially access modifiers and class members/methods in Java/C#-style definitions.

    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
     kasarigan
    -0.85
    Personendaten
    -0.85
     كومونز
    -0.78
    OGND
    -0.77
     мәкал
    -0.72
     &___
    -0.72
    Javadoc
    -0.72
    PyExc
    -0.71
     Biôgrafia
    -0.68
    BufferException
    -0.67
    POSITIVE LOGITS
     bool
    0.82
     boolean
    0.77
    bool
    0.77
     int
    0.74
    boolean
    0.68
    int
    0.67
     string
    0.60
     float
    0.58
    String
    0.57
     String
    0.57
    Activations Density 0.206%

    No Known Activations