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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 96441
    Prev
    Next
    INDEX
    Explanations

    phrases related to research findings or results in scientific studies

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

    findings suggest or imply

    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
    AutoresizingMask
    -0.71
    ⓧ
    -0.67
     maș
    -0.66
    ſelves
    -0.65
    alakip
    -0.62
    chränk
    -0.60
    majánló
    -0.60
    antwoorde
    -0.60
    ſelf
    -0.59
    uzzy
    -0.58
    POSITIVE LOGITS
     findings
    1.75
     Findings
    1.63
    Findings
    1.59
     FINDINGS
    1.38
     hallaz
    0.88
    FIND
    0.76
    finding
    0.75
     finding
    0.75
     Finding
    0.73
    find
    0.69
    Activations Density 0.018%

    No Known Activations