© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 6317
    Prev
    Next
    INDEX
    Explanations

    phrases indicating processes or outcomes of actions and evaluations

    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
     فريبيس
    -0.37
    瘩
    -0.33
     Claw
    -0.33
     claw
    -0.33
    hal
    -0.33
    haram
    -0.32
    leute
    -0.32
    Claw
    -0.31
    연
    -0.31
    du
    -0.31
    POSITIVE LOGITS
     ModelRenderer
    0.65
    EndInit
    0.60
    ValueStyle
    0.59
     useAppContext
    0.57
    +#+#
    0.56
    WebElementEntity
    0.56
     continúas
    0.56
     defaultstate
    0.55
    postsleuth
    0.54
    SharedDtor
    0.54
    Activations Density 0.901%

    No Known Activations