© 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. 31201
    Prev
    Next
    INDEX
    Explanations

    references to the Taliban and events related to conflict or terrorism

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

    Taliban actions and code syntax

    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
    Twitch
    -0.51
     للاسماء
    -0.49
     Twitch
    -0.48
    WaitGroup
    -0.48
     streamers
    -0.46
     twitch
    -0.43
    AndEndTag
    -0.42
    twitch
    -0.41
    BASELINE
    -0.40
    lwjgl
    -0.40
    POSITIVE LOGITS
    principalColumn
    0.42
    parsedMessage
    0.41
     cell
    0.41
    GEBURTS
    0.40
     समीक्षाओं
    0.39
    Cordial
    0.38
     dialog
    0.37
     propOrder
    0.37
    gång
    0.37
    längerung
    0.37
    Activations Density 0.022%

    No Known Activations