© 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-2-2B
    4. Residual Stream - 16k
    5. 4-GEMMASCOPE-RES-16K
    6. 16320
    Prev
    Next
    INDEX
    Explanations

    sections marked or formatted with special characters or headings

    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
    ensement
    -0.70
     Treff
    -0.64
    nesc
    -0.64
    */)
    -0.63
    ()")
    -0.63
    gäng
    -0.63
     }}"></
    -0.62
     Arca
    -0.61
    ?")
    -0.61
    ----------
    
    -0.61
    POSITIVE LOGITS
     |
    2.26
     $|
    1.74
    |
    1.62
    .|
    1.50
     $|\
    1.50
    }|
    1.49
    -|
    1.48
    "|
    1.47
    +|
    1.47
    $|
    1.46
    Activations Density 0.086%

    No Known Activations