© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 45797
    Prev
    Next
    INDEX
    Explanations

    terms related to "active" status or states in various contexts

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

    active state

    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
    smtp
    -0.28
     itself
    -0.28
     delin
    -0.27
    ysacchar
    -0.27
    cimientos
    -0.26
     deix
    -0.26
    ühr
    -0.25
     Mérimée
    -0.25
    https
    -0.25
     herum
    -0.25
    POSITIVE LOGITS
    active
    2.03
     active
    1.96
     ACTIVE
    1.55
     Active
    1.52
    Active
    1.45
    ACTIVE
    1.39
     actif
    1.34
     activo
    1.32
     aktiven
    1.30
     aktive
    1.27
    Activations Density 0.003%

    No Known Activations