© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 8826
    Prev
    Next
    INDEX
    Explanations

    elements related to functions and methods in programming or code

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

    Code snippets

    np_acts-logits-general · gemini-2.0-flash

    HTML closing tags and code snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     AssemblyCompany
    -0.80
    RTEE
    -0.79
    featureID
    -0.78
     queſta
    -0.77
    ValueStyle
    -0.75
    zzleHttp
    -0.75
    SpringRunner
    -0.74
     MainAxisSize
    -0.74
     мәкал
    -0.71
    kloped
    -0.71
    POSITIVE LOGITS
    0
    0.40
    ，
    0.34
     deberán
    0.33
    ↵
    0.32
    1
    0.31
    </td>
    0.30
    $\
    0.29
     we
    0.28
    So
    0.28
    ']))
    0.28
    Activations Density 0.065%

    No Known Activations