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. 128896
    Prev
    Next
    INDEX
    Explanations

    technical terms and descriptors related to mechanical and programming components

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

    string, plate, bolt, bar, code

    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
     utafitiHapana
    -0.63
     ModelExpression
    -0.54
    Portail
    -0.53
    ſelben
    -0.52
    ressee
    -0.50
    erati
    -0.50
     EconPapers
    -0.48
    PMailer
    -0.48
    ロウィン
    -0.48
     MainAxisSize
    -0.48
    POSITIVE LOGITS
    GEBURTSDATUM
    0.34
     Audiodateien
    0.33
    CrossOrigin
    0.32
    SpringRunner
    0.31
     للاسماء
    0.30
    糸
    0.30
    oredCriteria
    0.29
    ソッド
    0.28
    LookAnd
    0.28
    SwitchCompat
    0.28
    Activations Density 0.457%

    No Known Activations