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. 114038
    Prev
    Next
    INDEX
    Explanations

    specified phrases or words that denote constraints or limitations

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

    mode, state, class, limit

    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
     aarde
    -0.38
     iconTwitter
    -0.37
    Kanpo
    -0.36
    Ắ
    -0.36
    mbira
    -0.35
     suatu
    -0.35
    Fund
    -0.35
     ontwikkeling
    -0.34
     conflicts
    -0.34
     affari
    -0.33
    POSITIVE LOGITS
    ⤹
    0.66
    DockStyle
    0.66
    ScopeManager
    0.59
    OGND
    0.57
    utilisons
    0.56
     defaultstate
    0.56
    oredCriteria
    0.56
    ResumeLayout
    0.54
    IntoConstraints
    0.49
     وتسجيلات
    0.49
    Activations Density 0.015%

    No Known Activations