© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 75965
    Prev
    Next
    INDEX
    Explanations

    references to political scandals and allegations

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

    investigation and indictment of politicians

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Indented
    -0.38
     PeEnEo
    -0.34
    ksikon
    -0.34
    word
    -0.31
     كومونز
    -0.31
     Dade
    -0.30
     cim
    -0.30
    GoogleApiClient
    -0.29
    ADR
    -0.29
    Op
    -0.29
    POSITIVE LOGITS
     scandals
    0.58
     investigations
    0.56
     revelations
    0.54
    +#+#
    0.54
     Untersuch
    0.52
     dénon
    0.52
     investigação
    0.51
    PerformLayout
    0.51
    Investigations
    0.51
    ロウィン
    0.50
    Activations Density 0.053%

    No Known Activations