© 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. 19-GEMMASCOPE-RES-16K
    6. 11403
    Prev
    Next
    INDEX
    Explanations

    string literals and array representations 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 @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -0.65
    </em>
    -0.63
    </h3>
    -0.62
    ,
    -0.61
     so
    -0.60
     and
    -0.59
     po
    -0.58
    </strong>
    -0.57
    ...
    
    -0.56
    )))
    
    -0.56
    POSITIVE LOGITS
     للمعارف
    1.18
     pleaſure
    1.16
    ["
    1.12
     myſelf
    1.09
     ſp
    1.03
     Monfieur
    1.01
    (["
    1.00
     juſt
    1.00
     ['./
    0.99
     Verſ
    0.98
    Activations Density 0.190%

    No Known Activations