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. 170
    Prev
    Next
    INDEX
    Explanations

    URLs and hyperlinks in the text

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

    URLs

    np_acts-logits-general · gemini-2.0-flash

    URL prefixes after `://`

    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
    SuppressLint
    -0.46
    geral
    -0.42
    AndroidJUnit
    -0.42
     overal
    -0.42
    yczna
    -0.41
    WritableDatabase
    -0.41
    tahui
    -0.40
    HasKey
    -0.40
    cloudflare
    -0.40
    liken
    -0.39
    POSITIVE LOGITS
    脚注の使い方
    0.73
    Vidite
    0.70
    
    0.69
    migrationBuilder
    0.69
    rungsseite
    0.65
    RegressionTest
    0.63
    Portail
    0.62
     podjela
    0.62
     useAuth
    0.62
    CppMethod
    0.62
    Activations Density 0.186%

    No Known Activations