Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 31-GEMMASCOPE-RES-16K
    6. 3266
    Prev
    Next
    INDEX
    Explanations

    references to legal concepts and proceedings

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    proper nouns and formal titles or names of specific institutions and positions.

    oai_token-act-pair · claude-4-5-haikuTriggered by @emiglarou
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 31-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_31/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    selen
    -0.40
    vedra
    -0.35
     dintr
    -0.35
     Specially
    -0.35
    ENSIVE
    -0.34
    号
    -0.34
     Eu
    -0.34
    MockMvc
    -0.33
     Mell
    -0.33
     internal
    -0.33
    POSITIVE LOGITS
     متعلقه
    0.70
    RenderAtEndOf
    0.58
    RectangleBorder
    0.58
    Manbalar
    0.54
    verifyException
    0.53
    DockStyle
    0.52
     pinulongan
    0.52
    StoreMessageInfo
    0.51
     '\\;'
    0.49
    HtmlAttribute
    0.47
    Activations Density 1.250%

    No Known Activations