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. 21-GEMMASCOPE-RES-16K
    6. 13753
    Prev
    Next
    INDEX
    Explanations

    words or names associated with individuals whose first name starts with "Ke."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    LookAnd
    -0.94
    RegressionTest
    -0.79
    )++;
    -0.78
    EndProject
    -0.73
     itſelf
    -0.71
    aarrggbb
    -0.71
     vuitton
    -0.71
    +#+
    -0.71
    retweeted
    -0.70
     surla
    -0.70
    POSITIVE LOGITS
     combineReducers
    0.53
    withIdentifier
    0.50
     WebDriverWait
    0.46
     EconPapers
    0.44
    ke
    0.43
     kele
    0.42
     Ke
    0.41
    tel
    0.40
     densité
    0.40
    Gotcha
    0.40
    Activations Density 0.067%

    No Known Activations