© 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. 0-GEMMASCOPE-RES-65K
    6. 9909
    Prev
    Next
    INDEX
    Explanations

    phrases or instances where the word "by" is used, indicating an action or attribution

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_65k/average_l0_73
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    [
    -0.61
    A
    -0.56
    N
    -0.54
    O
    -0.53
    T
    -0.52
    I
    -0.51
    H
    -0.51
    ورد
    -0.51
    P
    -0.51
    B
    -0.50
    POSITIVE LOGITS
     by
    1.34
     defaultstate
    1.07
     Roskov
    0.99
     estekak
    0.97
    ViewImports
    0.96
    Personendaten
    0.96
    ]")]
    0.94
     fieldNum
    0.93
    AndEndTag
    0.93
     kasarigan
    0.92
    Activations Density 0.231%

    No Known Activations