© 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. 11-GEMMASCOPE-RES-16K
    11. 4858
    Prev
    Next
    INDEX
    Explanations

    information related to significant achievements and innovations in various fields

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    leroi
    -0.41
     trattano
    -0.41
    tend
    -0.40
     bicchiere
    -0.40
     Ting
    -0.39
     tend
    -0.39
    Browsable
    -0.39
     désert
    -0.38
     Motherboard
    -0.38
    tershire
    -0.38
    POSITIVE LOGITS
    AnchorStyles
    0.49
    Referencies
    0.49
    !(:
    0.44
    WithMany
    0.43
    //
    0.42
    SourceChecksum
    0.42
     eventual
    0.41
    RTLU
    0.41
     später
    0.40
     ultimately
    0.40
    Activations Density 0.832%

    No Known Activations