© 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-IT
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 7172
    Prev
    Next
    INDEX
    Explanations

    emphasized themes or concepts related to content availability and updates

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

    Code or configuration data

    np_acts-logits-general · gemini-2.0-flash

    api, background, view, protocol

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_16k/average_l0_88
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     întâ
    -0.50
    Personendaten
    -0.49
     membuatnya
    -0.46
    ofür
    -0.46
    contentLoaded
    -0.45
     gevallen
    -0.43
    uxxxx
    -0.43
     financière
    -0.43
    seamnă
    -0.42
    chieht
    -0.42
    POSITIVE LOGITS
    !(:
    0.48
    chol
    0.46
     native
    0.45
    Coordonnées
    0.44
    OrNil
    0.44
     Zeb
    0.44
     buried
    0.44
     repressed
    0.43
    Portale
    0.42
     indigenous
    0.42
    Activations Density 0.457%

    No Known Activations