© 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. 10096
    Prev
    Next
    INDEX
    Explanations

    terminology related to socioeconomic status indicators

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

    sessile, sesame, session

    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
     arşivlendi
    -0.50
     Blackwell
    -0.50
    Portale
    -0.46
    Takk
    -0.45
     Alton
    -0.44
    marvin
    -0.44
     Nuevo
    -0.43
     Ashton
    -0.41
     Chino
    -0.41
    Diámetro
    -0.40
    POSITIVE LOGITS
     Ses
    2.27
    Ses
    2.25
    ses
    2.25
     ses
    2.22
     SES
    1.97
    SES
    1.95
     Sess
    1.19
     Sesame
    1.18
     sesame
    1.17
     session
    1.14
    Activations Density 0.006%

    No Known Activations