© 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. 3-GEMMASCOPE-RES-16K
    11. 12649
    Prev
    Next
    INDEX
    Explanations

    characters and names related to a fantasy narrative or adventure story

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itſelf
    -0.81
     greateſt
    -0.80
    wość
    -0.71
     themſelves
    -0.70
     venons
    -0.70
     препратки
    -0.69
     ligiloj
    -0.69
     raiſ
    -0.68
    ftance
    -0.68
     pinulongan
    -0.67
    POSITIVE LOGITS
     RemoteException
    0.70
    providedIn
    0.69
     novia
    0.52
    Życiorys
    0.52
     I
    0.50
    ContentAsync
    0.49
    setScene
    0.49
     &___
    0.46
     vPvB
    0.46
     we
    0.46
    Activations Density 0.149%

    No Known Activations