© 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. 3322
    Prev
    Next
    INDEX
    Explanations

    phrases related to application features or updates

    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
    ModelAttribute
    -0.49
    DeleteMapping
    -0.43
     colgante
    -0.43
     pungkasnya
    -0.42
     competencia
    -0.42
     clínico
    -0.41
     competición
    -0.41
     reproducción
    -0.41
     redacción
    -0.41
     récompense
    -0.41
    POSITIVE LOGITS
     BoxFit
    0.63
    timezone
    0.60
     GMT
    0.60
     UTC
    0.60
    GMT
    0.57
     timezone
    0.56
    TimeZone
    0.55
    AndEndTag
    0.53
    CloseOperation
    0.52
    UTC
    0.50
    Activations Density 0.215%

    No Known Activations