© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 102399
    Prev
    Next
    INDEX
    Explanations

    abstract concepts and generalized statements regarding various topics

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot

    general statements

    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
    Negative Logits
    
    -0.67
    ValueStyle
    -0.51
    adaptiveStyles
    -0.51
    EXCLUSIVE
    -0.49
     EXCLUSIVE
    -0.48
    tificial
    -0.46
     exclusivity
    -0.46
    EndContext
    -0.45
    $_['
    -0.44
     gynhyrchwyd
    -0.44
    POSITIVE LOGITS
     general
    1.55
    general
    1.41
    General
    1.30
     General
    1.27
     generales
    1.22
     général
    1.20
     GENERAL
    1.16
    GENERAL
    1.15
     allgemeine
    1.13
     geral
    1.12
    Activations Density 0.151%

    No Known Activations