© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 4-GEMMASCOPE-RES-16K
    11. 849
    Prev
    Next
    INDEX
    Explanations

    elements related to design and style

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -0.86
    SBATCH
    -0.78
    PreExecute
    -0.77
     MainAxisSize
    -0.76
    protoimpl
    -0.74
    endpush
    -0.71
     ffilm
    -0.71
    StoryboardSegue
    -0.69
    uxxxx
    -0.69
     doInBackground
    -0.68
    POSITIVE LOGITS
     style
    1.57
     Style
    1.41
     styles
    1.30
     STYLE
    1.23
     estilo
    1.23
     styl
    1.22
    Style
    1.20
    style
    1.18
     stile
    1.08
     Styles
    1.08
    Activations Density 0.460%

    No Known Activations