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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10290
    Prev
    Next
    INDEX
    Explanations

    variables, return statements, and object-oriented structure elements in code

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

    Chaining or returning "this" or "self"

    np_acts-logits-general · gemini-2.0-flash

    object references: this, self

    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
    aarrggbb
    -0.64
    windowFixed
    -0.55
    ftagPool
    -0.53
    يكب
    -0.53
    NameInMap
    -0.53
    MigrationBuilder
    -0.46
    mybatisplus
    -0.46
    LookAnd
    -0.46
    الحياه
    -0.45
    ंदीखरीदारी
    -0.45
    POSITIVE LOGITS
     myself
    1.31
     Myself
    1.23
     ourselves
    1.20
    Myself
    1.19
    myself
    1.19
    self
    1.14
     oneself
    1.11
     yourself
    1.08
     themselves
    1.08
     himself
    1.07
    Activations Density 0.210%

    No Known Activations