© 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-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 5595
    Prev
    Next
    INDEX
    Explanations

    keywords associated with food ingredients and medical terms

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    BagLayout
    -0.55
     kotlinx
    -0.53
     getLast
    -0.51
    zzleHttp
    -0.51
    JLabel
    -0.48
     KN
    -0.47
     Illuminate
    -0.46
    featureID
    -0.45
     Hist
    -0.45
     Lemma
    -0.44
    POSITIVE LOGITS
     ProtoMessage
    0.36
     telefónica
    0.34
     draußen
    0.34
    outchouc
    0.33
     sekali
    0.33
     pngtree
    0.32
     posesión
    0.31
     PopupWindow
    0.30
     Pública
    0.30
    RenderAtEndOf
    0.30
    Activations Density 0.234%

    No Known Activations