© 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
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 12933
    Prev
    Next
    INDEX
    Explanations

    programming-related identifiers and variables used in defining functions and object properties

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

    Code or configuration file-related text

    np_acts-logits-general · gemini-2.0-flash

    technical definitions and assignments

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Negative Logits
    verwijspagina
    -0.85
     transfieras
    -0.80
     queſta
    -0.73
     يتيمه
    -0.73
     gyhoeddwyd
    -0.71
    adpleegd
    -0.71
     Efq
    -0.68
     للمعارف
    -0.68
    FontOfSize
    -0.67
     Monfieur
    -0.67
    POSITIVE LOGITS
     is
    0.53
     was
    0.52
     =
    0.46
     consists
    0.38
     includes
    0.34
     will
    0.32
     consisted
    0.31
     wasn
    0.30
     depends
    0.30
     are
    0.30
    Activations Density 0.273%

    No Known Activations