© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 968
    Prev
    Next
    INDEX
    Explanations

    patterns of underscores and asterisks, which may indicate placeholders or emphasis in the text formatting

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tagHelperRunner
    -0.74
     GenerationType
    -0.74
     Monfieur
    -0.73
     foon
    -0.71
     Efq
    -0.71
     onCreateView
    -0.70
    UserScript
    -0.70
     الحره
    -0.70
    FormTagHelper
    -0.69
    Autoritní
    -0.68
    POSITIVE LOGITS
     really
    0.56
     exactly
    0.52
    <i>
    0.51
     (!
    0.49
    ‘
    0.49
     choix
    0.46
     even
    0.45
    раздо
    0.45
     actually
    0.45
     itself
    0.45
    Activations Density 0.122%

    No Known Activations