© 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. 22-GEMMASCOPE-RES-16K
    11. 10552
    Prev
    Next
    INDEX
    Explanations

    HTML tags or elements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    HTML code snippets

    np_acts-logits-general · gemini-2.0-flash

    closing tags and brackets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     MotionEvent
    -0.76
     contextLoads
    -0.74
    VersionUID
    -0.71
     Мексичка
    -0.68
    ProcessEvent
    -0.67
     gyhoeddwyd
    -0.61
    ParallelGroup
    -0.60
     AssemblyCompany
    -0.58
    ConstraintMaker
    -0.58
     '{@
    -0.58
    POSITIVE LOGITS
    ↵↵
    0.69
    <eos>
    0.64
    "]}
    0.61
    ↵
    0.56
    ↵↵↵
    0.55
    <tr>
    0.54
    ')}
    0.54
     
    0.53
    </table>
    0.53
     }}>
    0.52
    Activations Density 0.109%

    No Known Activations