© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 13371
    Prev
    Next
    INDEX
    Explanations

    variations of the word "be" in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.80
    wußt
    -0.73
    extAlignment
    -0.71
    principalColumn
    -0.70
    awtextra
    -0.68
    GeoNames
    -0.67
    multer
    -0.67
    fjspx
    -0.63
     Económica
    -0.62
     MainAxisSize
    -0.62
    POSITIVE LOGITS
     Be
    0.83
    Be
    0.79
    bea
    0.67
    be
    0.67
    BE
    0.64
     BE
    0.64
    bei
    0.56
     Bech
    0.55
     Bef
    0.54
     Bew
    0.53
    Activations Density 0.187%

    No Known Activations