Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 11897
    Prev
    Next
    INDEX
    Explanations

    elements and functions related to form handling in a programming context

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

    JavaScript class/object definitions

    np_acts-logits-general · gemini-2.0-flash

    JavaScript class and prototype definitions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.66
     calldata
    -0.64
     препратки
    -0.62
     وتسجيلات
    -0.59
     InputDecoration
    -0.58
     JADX
    -0.58
    GrantedAuthority
    -0.56
     informée
    -0.55
    WriteAttribute
    -0.54
     nướng
    -0.53
    POSITIVE LOGITS
     class
    0.64
    createClass
    0.64
    class
    0.63
    LookAnd
    0.60
    prototype
    0.59
    WebControls
    0.58
    /**
    0.57
     inherits
    0.55
    extend
    0.55
    inherits
    0.54
    Activations Density 0.161%

    No Known Activations