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. 69149
    Prev
    Next
    INDEX
    Explanations

    structured programming elements and syntax in code

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

    task at hand

    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
    inSlope
    -0.47
    GraphicsUnit
    -0.35
     jajaran
    -0.34
    Bronnen
    -0.32
    出版年
    -0.31
     zasi
    -0.31
     czuj
    -0.31
     skydd
    -0.31
    setEnd
    -0.31
     cliquant
    -0.31
    POSITIVE LOGITS
     tasks
    1.30
     task
    1.23
     Tasks
    1.21
    tasks
    1.18
    Tasks
    1.10
    task
    1.09
     Task
    1.04
     TASK
    1.02
    Task
    1.00
     tareas
    0.97
    Activations Density 0.037%

    No Known Activations