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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 9-GEMMASCOPE-RES-131K
    6. 90736
    Prev
    Next
    INDEX
    Explanations

    quantitative and evaluative details related to measures of significance

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

    abstract nouns and measurements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 9-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_9/width_131k/average_l0_121
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Photocase
    -0.63
     المعيارى
    -0.59
    MemoryWarning
    -0.54
    FieldNumber
    -0.54
    TagNumber
    -0.54
    twimg
    -0.50
    IActionResult
    -0.48
    transQ
    -0.47
    alakip
    -0.47
    IntoConstraints
    -0.46
    POSITIVE LOGITS
     automatique
    0.43
     financière
    0.41
     Verfügung
    0.39
    uttavia
    0.37
     moeite
    0.37
     económica
    0.37
    TagMode
    0.36
     indiví
    0.36
     Vision
    0.35
     économique
    0.35
    Activations Density 0.125%

    No Known Activations