© 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. 10-GEMMASCOPE-RES-16K
    11. 12502
    Prev
    Next
    INDEX
    Explanations

    words associated with performance metrics and biological changes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tivamente
    -0.56
    tearDown
    -0.50
    ποτε
    -0.49
     jäsen
    -0.49
    WritableDatabase
    -0.48
    niosek
    -0.47
     lemah
    -0.46
     üzere
    -0.46
     оно
    -0.46
     of
    -0.46
    POSITIVE LOGITS
    <!--[
    0.70
     Roskov
    0.70
    rawDesc
    0.69
     متعلقه
    0.67
    انيف
    0.66
    PreAuthorize
    0.62
    ########.
    0.62
    ритори
    0.61
    tvguidetime
    0.60
     تضيفلها
    0.58
    Activations Density 1.089%

    No Known Activations