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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 31-GEMMASCOPE-RES-131K
    6. 20246
    Prev
    Next
    INDEX
    Explanations

    numerical data and references commonly found in academic and scientific publications

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

    numbers followed by punctuation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beat
    -0.30
     лежит
    -0.27
     routine
    -0.27
     totally
    -0.26
     travail
    -0.25
    ::
    -0.25
     اك
    -0.25
     
    -0.25
    <bos>
    -0.25
    geist
    -0.24
    POSITIVE LOGITS
    UnusedPrivate
    0.75
    tagext
    0.71
     المعيارى
    0.68
     Normdatei
    0.67
    SourceChecksum
    0.61
    elemField
    0.60
     Verſ
    0.59
    prepareStatement
    0.59
    migrationBuilder
    0.59
    ]")]
    0.58
    Activations Density 0.069%

    No Known Activations