© 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. 45479
    Prev
    Next
    INDEX
    Explanations

    instances of the term "intervention" and related forms in various contexts

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

    intervene, intervention, intervening

    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
    arnya
    -0.37
     relever
    -0.34
     frit
    -0.32
     lists
    -0.31
    DIRECTORY
    -0.31
    mago
    -0.30
     Prepar
    -0.30
    Def
    -0.30
     condi
    -0.29
    Motiv
    -0.29
    POSITIVE LOGITS
     intervention
    1.46
     intervene
    1.45
     intervened
    1.44
    Intervention
    1.40
    intervention
    1.37
     interventions
    1.36
     Intervention
    1.35
     interven
    1.32
     intervenir
    1.30
     Interventions
    1.29
    Activations Density 0.042%

    No Known Activations