© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B-IT
    7. Residual Stream - 131k
    9. 9-GEMMASCOPE-RES-131K
    11. 58815
    Prev
    Next
    INDEX
    Explanations

    negative terms or phrases associated with reductions or declines

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

    hyphenated words

    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
     increí
    -0.94
     müſſen
    -0.93
    majánló
    -0.93
     laſſen
    -0.93
    parsedMessage
    -0.92
     NSCoder
    -0.91
    httphttps
    -0.91
    <unused74>
    -0.90
    <unused41>
    -0.90
    <unused14>
    -0.90
    POSITIVE LOGITS
    -
    1.55
    ‐
    0.81
    _
    0.81
    –
    0.73
    '-
    0.72
    -(
    0.71
     -
    0.70
    $-
    0.70
    -\
    0.69
    -,
    0.69
    Activations Density 0.803%

    No Known Activations