Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 672
    Prev
    Next
    INDEX
    Explanations

    references to conditions or requirements regarding social or legal expectations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Houſe
    -0.44
    SharedDtor
    -0.42
     Majefty
    -0.41
     oprot
    -0.40
     purpoſe
    -0.39
    Види
    -0.39
     Partie
    -0.39
     jura
    -0.39
     scène
    -0.38
     Cæsar
    -0.37
    POSITIVE LOGITS
     للمعارف
    0.69
    onOptions
    0.52
     ddelweddau
    0.50
     ayaa
    0.48
     aanz
    0.47
     finally
    0.45
    seitig
    0.45
     chi̍t
    0.45
     μπο
    0.45
     helemaal
    0.44
    Activations Density 1.059%

    No Known Activations