© 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. 12-GEMMASCOPE-RES-16K
    6. 1853
    Prev
    Next
    INDEX
    Explanations

    phrases related to areas needing improvement or development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.32
     guests
    -0.32
    式
    -0.32
     sve
    -0.30
     pur
    -0.29
     zare
    -0.27
    c
    -0.26
     Bildungs
    -0.26
     appropriate
    -0.25
    orElseThrow
    -0.25
    POSITIVE LOGITS
     disambiguazione
    0.90
     Areas
    0.79
     areas
    0.77
    areas
    0.74
    FunctionFlags
    0.72
    Areas
    0.71
     AREAS
    0.71
    IBOutlet
    0.68
     áreas
    0.67
    そこは
    0.66
    Activations Density 0.748%

    No Known Activations