© 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 EvalsExportsinterp-engineNEWAPI 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. 81930
    Prev
    Next
    INDEX
    Explanations

    instances of the word "outspoken" and expressions that convey summary or essential information

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

    outspoken, nutshell, pivotal study

    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
    ransition
    -0.59
    astify
    -0.57
     FetchType
    -0.57
    MigrationBuilder
    -0.56
     createState
    -0.54
    TemporalType
    -0.50
    Slf
    -0.48
    ském
    -0.47
    onedDateTime
    -0.47
     Bulb
    -0.47
    POSITIVE LOGITS
     outspoken
    1.15
     betweenstory
    0.56
    eſ
    0.47
    oporosis
    0.43
     unſ
    0.41
     indispensable
    0.40
    iſt
    0.40
     speechless
    0.39
    propor
    0.39
    estimable
    0.39
    Activations Density 0.005%

    No Known Activations