© 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. 23-GEMMASCOPE-RES-16K
    6. 9615
    Prev
    Next
    INDEX
    Explanations

    elements related to programming structures and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.44
     kapturem
    -0.37
     kasarigan
    -0.37
    guenos
    -0.36
    XmlAccessorType
    -0.36
    SEGUIR
    -0.35
    itinéraire
    -0.35
    fromCharCode
    -0.34
     expédié
    -0.33
    TAGE
    -0.33
    POSITIVE LOGITS
    ScopeManager
    0.62
    Datuak
    0.52
     قب
    0.50
    apimachinery
    0.48
    EDEFAULT
    0.47
    ########.
    0.47
     vänt
    0.46
     OFDb
    0.45
     للاسماء
    0.45
     previously
    0.44
    Activations Density 0.432%

    No Known Activations