© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 4289
    Prev
    Next
    INDEX
    Explanations

    instances where the verb "inform" is used, indicating communication or dissemination of information

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

    inform and guide development

    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
     Wayback
    -0.55
    arriver
    -0.53
     Abbey
    -0.53
     Meksika
    -0.52
     Duca
    -0.50
    Abbey
    -0.50
    Cada
    -0.50
     rowCount
    -0.49
     aéri
    -0.48
    ientôt
    -0.48
    POSITIVE LOGITS
     inform
    1.78
    Inform
    1.73
     Inform
    1.73
    inform
    1.70
     informs
    1.30
     INFORM
    1.28
     informing
    1.23
    INFORM
    1.19
     informar
    1.13
     informant
    1.05
    Activations Density 0.014%

    No Known Activations