© 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. 3272
    Prev
    Next
    INDEX
    Explanations

    conjunctions and repetitions in phrases

    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
     ostavi
    -0.89
    NegativeButton
    -0.80
     faſt
    -0.79
     indisponible
    -0.76
    RenderAtEndOf
    -0.75
     nakalista
    -0.73
     <",
    -0.73
    liothèque
    -0.73
     uſed
    -0.71
    PositiveButton
    -0.70
    POSITIVE LOGITS
    SerializeField
    0.52
    inf
    0.51
     χω
    0.47
    var
    0.46
    providedIn
    0.45
    </b>
    0.45
     terlebih
    0.45
     kari
    0.44
     frein
    0.44
    I
    0.44
    Activations Density 0.138%

    No Known Activations