© 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. 20-GEMMASCOPE-RES-131K
    11. 73151
    Prev
    Next
    INDEX
    Explanations

    phrases related to providing information, assistance, or instructions

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

    information and related details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    principalColumn
    -0.79
     protoimpl
    -0.75
    Parcelize
    -0.58
    ValueStyle
    -0.57
    PerformLayout
    -0.57
    WriteTagHelper
    -0.55
     lenker
    -0.52
    homonymie
    -0.51
    AutoScaleMode
    -0.50
     HFILL
    -0.49
    POSITIVE LOGITS
    Personendaten
    0.39
     незавершена
    0.38
     înal
    0.33
     see
    0.31
    literals
    0.30
     réserve
    0.29
    詳細は
    0.29
     tiks
    0.29
    かは
    0.28
    For
    0.28
    Activations Density 0.020%

    No Known Activations