© 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 - 65k
    5. 13-GEMMASCOPE-RES-65K
    6. 14762
    Prev
    Next
    INDEX
    Explanations

    the presence of start-of-sequence tokens

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 13-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_13/width_65k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.13.hook_resid_post
    Hook Layer
    13
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </h2>
    -0.59
    หวัด
    -0.55
     …
    -0.54
    </i>
    -0.51
    </h5>
    -0.50
    </em>
    -0.48
    didSet
    -0.48
    JoinColumn
    -0.46
    bootstrapcdn
    -0.46
    </u>
    -0.46
    POSITIVE LOGITS
     Roskov
    0.86
     مرئيه
    0.71
     autorytatywna
    0.66
     forState
    0.65
    RTEE
    0.60
    setDo
    0.60
    expandindo
    0.59
     الاطلاع
    0.59
     CURLOPT
    0.58
     bezeichneter
    0.58
    Activations Density 0.001%

    No Known Activations