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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 10666
    Prev
    Next
    INDEX
    Explanations

    quotation marks and special characters in the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    confirmPassword
    -0.53
     in
    -0.52
    er
    -0.49
     developed
    -0.48
    Đây
    -0.48
     as
    -0.47
     and
    -0.47
     nhu
    -0.47
     cố
    -0.47
     on
    -0.45
    POSITIVE LOGITS
    MigrationBuilder
    1.02
     Wiktionnaire
    0.88
    وردار
    0.84
    principalColumn
    0.77
    сылкі
    0.76
    rungsseite
    0.76
     numberWith
    0.74
     SIMBAD
    0.74
    \{\\
    0.72
    DrawerToggle
    0.71
    Activations Density 0.084%

    No Known Activations