© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 1848
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transitions that indicate contrast or addition in sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ItemBackground
    -0.67
     Exacts
    -0.60
    lalom
    -0.58
    InitVars
    -0.58
     ơn
    -0.57
     allAfrica
    -0.57
     poto
    -0.56
    évolution
    -0.56
     intermit
    -0.56
    icoot
    -0.55
    POSITIVE LOGITS
    HasAnnotation
    0.66
    </s>
    0.65
    basicConfig
    0.65
    IntoConstraints
    0.62
     للمعارف
    0.61
    EndProject
    0.59
    rrbracket
    0.59
    tangentMode
    0.55
    ADATA
    0.53
    mipmap
    0.52
    Activations Density 0.511%

    No Known Activations