© 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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 115476
    Prev
    Next
    INDEX
    Explanations

    jQuery or JavaScript selector syntax

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

    jquery selectors for html elements

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    _
    
    -0.52
    ]')
    -0.51
    itemize
    -0.51
    ]")
    -0.50
    Slf
    -0.48
    '):
    
    -0.46
     ep
    -0.45
     Sim
    -0.44
    ]_
    -0.44
     Ev
    -0.43
    POSITIVE LOGITS
    pecabe
    0.87
     $('
    0.83
     $("
    0.82
     $("<
    0.80
     Económica
    0.80
    $('
    0.79
     $('.
    0.74
    $("
    0.74
     $(".
    0.73
     $('<
    0.71
    Activations Density 0.002%

    No Known Activations