Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 105083
    Prev
    Next
    INDEX
    Explanations

    code block structures and delimiters in programming syntax

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     EconPapers
    -0.61
     ब्रेकडाउन
    -0.56
     onPostExecute
    -0.54
    };*/
    -0.54
    TagMode
    -0.51
     Wikimedijinoj
    -0.49
    +#+#
    -0.48
     AspNetCore
    -0.48
    .*")]
    -0.48
    μως
    -0.46
    POSITIVE LOGITS
    AppMethodBeat
    0.37
    GEBURTSDATUM
    0.36
     تضيفلها
    0.34
     gl
    0.34
    TRAILING
    0.34
     lg
    0.32
     giảm
    0.31
    楽
    0.31
    GEBURTS
    0.31
    تقاوى
    0.31
    Activations Density 0.014%

    No Known Activations