© 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. 76238
    Prev
    Next
    INDEX
    Explanations

    HTML attributes related to language specifications

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

    language

    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
    findpost
    -0.71
    awtextra
    -0.68
    AlterField
    -0.66
    +#+#
    -0.63
    UnusedPrivate
    -0.61
    StoryboardSegue
    -0.56
    IBOutlet
    -0.56
    initComponents
    -0.54
     createSprite
    -0.54
    SequentialGroup
    -0.53
    POSITIVE LOGITS
     language
    0.71
     languages
    0.69
    language
    0.64
    Language
    0.59
     idioma
    0.58
     Language
    0.57
    languages
    0.56
     Languages
    0.55
     idiomas
    0.54
    Languages
    0.51
    Activations Density 0.001%

    No Known Activations