© 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-2-9B-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 10297
    Prev
    Next
    INDEX
    Explanations

    the visibility modifiers used in programming, specifically those associated with classes and properties

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

    Code-related "public" keyword

    np_acts-logits-general · gemini-2.0-flash

    public static async const

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    protoimpl
    -0.47
    ésult
    -0.47
    FormTagHelper
    -0.47
    ñores
    -0.46
    SPJ
    -0.44
    ientras
    -0.44
     feroit
    -0.42
     itſelf
    -0.42
     estekak
    -0.42
    ----</
    -0.42
    POSITIVE LOGITS
    public
    2.00
     public
    1.39
    Public
    1.24
     Public
    1.20
     PUBLIC
    1.04
    PUBLIC
    1.00
    private
    0.86
     pública
    0.85
    ublic
    0.85
    公共
    0.79
    Activations Density 0.022%

    No Known Activations