© 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. 9-GEMMASCOPE-RES-131K
    6. 77967
    Prev
    Next
    INDEX
    Explanations

    technical terms related to engineering systems and geographic locations

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

    Cárthaigh, expanded fluid, drive side, Isfahan Province

    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
    AsUp
    -0.39
    üttel
    -0.35
     d
    -0.32
     Northumberland
    -0.29
     twar
    -0.29
     Utara
    -0.28
     Xue
    -0.28
    ministrazione
    -0.27
     kald
    -0.27
     northern
    -0.27
    POSITIVE LOGITS
     queſta
    0.76
     laſſen
    0.69
    rawDesc
    0.68
    parsedMessage
    0.65
     ſehr
    0.62
    <pad>
    0.60
    </tfoot>
    0.60
    ImageContext
    0.59
    <unused14>
    0.59
    <unused23>
    0.59
    Activations Density 0.120%

    No Known Activations