© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 18728
    Prev
    Next
    INDEX
    Explanations

    technical processes and methodologies related to extraction and treatment procedures

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

    algorithm eventually, routes put

    np_acts-logits-general · gemini-2.5-flash-lite

    the neuron's high activations mark salient technical/topic words and headings—content-bearing nouns and key terms in scientific or technical text.

    oai_token-act-pair · gpt-5-miniTriggered by @vetterc0
    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
     Comprometido
    -0.40
    Zubereitung
    -0.40
    HtmlAttribute
    -0.37
    }();
    -0.37
     Segurança
    -0.35
     problemática
    -0.32
     biologique
    -0.31
    tangentMode
    -0.31
     prisión
    -0.30
     MainAxisSize
    -0.30
    POSITIVE LOGITS
    Ӕ
    0.56
     InputDecoration
    0.52
    naio
    0.50
    gress
    0.48
    فایل‌لار
    0.46
     Definitive
    0.45
     IBOutlet
    0.44
    󠁴
    0.44
     остро
    0.44
    EDEFAULT
    0.44
    Activations Density 0.163%

    No Known Activations