© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 11-GEMMASCOPE-RES-16K
    6. 4783
    Prev
    Next
    INDEX
    Explanations

    patterns related to dates and numbers associated with historical events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 11-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_11/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Hook Layer
    11
    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
    -0.34
     זה
    -0.31
    ně
    -0.30
     jä
    -0.30
     wezen
    -0.28
    
    -0.28
     ברו
    -0.28
     перец
    -0.28
     vý
    -0.27
    ukone
    -0.27
    POSITIVE LOGITS
    ſelf
    0.63
    脚注の使い方
    0.60
     faſt
    0.58
     Monfieur
    0.56
    aarrggbb
    0.54
     houſe
    0.54
    írus
    0.53
     Reſ
    0.52
     ſche
    0.52
    +#+#
    0.52
    Activations Density 0.488%

    No Known Activations