© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 16256
    Prev
    Next
    INDEX
    Explanations

    serious events involving death or significant political actions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     mês
    -0.46
     fortnight
    -0.46
     desmotivaciones
    -0.45
     productivo
    -0.44
     mensuales
    -0.44
     esclavos
    -0.43
    几个月
    -0.43
     vacaciones
    -0.42
     veckor
    -0.42
    一个月
    -0.42
    POSITIVE LOGITS
    󠁴
    0.58
    MessageTagHelper
    0.57
     ProtoMessage
    0.56
    pexpr
    0.55
     wireType
    0.53
     GenerationType
    0.52
     afternoon
    0.50
    ⟬
    0.50
    afternoon
    0.50
    ChildScrollView
    0.50
    Activations Density 0.079%

    No Known Activations