© 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. 31-GEMMASCOPE-RES-16K
    6. 3576
    Prev
    Next
    INDEX
    Explanations

    occurrences of asterisks, indicating emphasis or importance in text

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

    words surrounded by asterisks or emphasized text.

    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
     of
    -0.25
     如
    -0.23
     with
    -0.22
    といって
    -0.21
    发表于
    -0.21
     entsprechenden
    -0.21
    Hozzáférés
    -0.21
    Externe
    -0.20
     amely
    -0.20
     center
    -0.20
    POSITIVE LOGITS
    DockStyle
    0.91
     propOrder
    0.90
    niſſe
    0.82
     Савезне
    0.81
     الرياضيه
    0.78
     müſſen
    0.77
    UnknownFieldSet
    0.76
     ویکی‌پدی
    0.76
    :✨
    0.75
    SourceChecksum
    0.74
    Activations Density 0.386%

    No Known Activations