Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 5945
    Prev
    Next
    INDEX
    Explanations

    references to returning items or refunds

    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
    ברה
    -0.76
    ykite
    -0.69
    valently
    -0.67
    Dougall
    -0.66
     cờ
    -0.63
    getKeyCode
    -0.63
    Farbe
    -0.62
     McCoy
    -0.61
    cheme
    -0.61
    Dammit
    -0.60
    POSITIVE LOGITS
    return
    1.37
     Return
    1.36
     RETURN
    1.36
     returns
    1.35
     Returns
    1.32
     Returned
    1.28
    Returned
    1.27
    Return
    1.26
     return
    1.25
     returned
    1.22
    Activations Density 0.079%

    No Known Activations