© 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. 31-GEMMASCOPE-RES-131K
    11. 63589
    Prev
    Next
    INDEX
    Explanations

    phrases related to intentions or actions indicating purpose or concern

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

    to me

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 31-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_31/width_131k/average_l0_109
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.31.hook_resid_post
    Hook Layer
    31
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RectangleBorder
    -0.57
    IsMutable
    -0.55
    featureID
    -0.55
     виправивши
    -0.48
     HasFactory
    -0.48
    fjspx
    -0.48
    RTLI
    -0.46
    ohist
    -0.45
    });*/
    -0.45
     arşivlendi
    -0.45
    POSITIVE LOGITS
     me
    1.85
     us
    1.11
     mnie
    0.99
     мне
    0.92
     меня
    0.82
    私は
    0.77
    me
    0.76
     comigo
    0.74
     tôi
    0.73
     मुझे
    0.72
    Activations Density 0.094%

    No Known Activations