© 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. 4-GEMMASCOPE-RES-16K
    11. 10055
    Prev
    Next
    INDEX
    Explanations

    code snippets within the text

    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
     
    -0.67
    เภ
    -0.64
    portlet
    -0.62
     Ort
    -0.60
    Titel
    -0.60
    showConfirm
    -0.59
     bios
    -0.59
     pant
    -0.58
     WPA
    -0.57
     ake
    -0.57
    POSITIVE LOGITS
    <code>
    2.39
    </code>
    1.33
     ```
    1.15
     `
    1.03
    [`
    1.00
     `"
    0.98
     (`
    0.97
    (`
    0.96
    :`
    0.96
    <th>
    0.95
    Activations Density 0.172%

    No Known Activations