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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 10295
    Prev
    Next
    INDEX
    Explanations

    declarations and visibility modifiers of classes and properties in a programming context

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

    C# public properties and methods

    np_acts-logits-general · gemini-2.0-flash

    public and protected declarations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    DoubleQuotes
    -0.73
     photolibrary
    -0.67
    parsedMessage
    -0.66
     DBNull
    -0.66
     findOne
    -0.66
     ModelRenderer
    -0.65
    IntoConstraints
    -0.65
     Shakspeare
    -0.63
     Nara
    -0.63
    ArrowToggle
    -0.62
    POSITIVE LOGITS
     override
    0.78
     string
    0.70
    string
    0.61
     bool
    0.58
     well
    0.57
    override
    0.56
     event
    0.49
    well
    0.49
    bool
    0.49
    InstrumentedTest
    0.47
    Activations Density 0.033%

    No Known Activations