© 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. 106580
    Prev
    Next
    INDEX
    Explanations

    names and titles of individuals and entities related to politics and media

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

    names of people

    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
    WireFormatLite
    -0.44
    ніципа
    -0.38
    ⓘ
    -0.36
    הערות
    -0.36
    jbl
    -0.36
     siir
    -0.35
    京
    -0.35
     feels
    -0.35
    蚪
    -0.35
    𓃵
    -0.34
    POSITIVE LOGITS
    ########.
    0.60
    tangentMode
    0.55
     beginnetje
    0.53
     незавершена
    0.51
     resourceCulture
    0.48
     disambiguazione
    0.48
     NUKAT
    0.48
     '\\;'
    0.47
    principalColumn
    0.47
    tagHelperRunner
    0.45
    Activations Density 0.200%

    No Known Activations