© 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. 1-GEMMASCOPE-RES-16K
    11. 11465
    Prev
    Next
    INDEX
    Explanations

    references to specific data targets or keys in a code context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    擅
    -0.40
     preferential
    -0.40
     inconvenient
    -0.38
     voluntary
    -0.36
     HTML
    -0.35
     supposedly
    -0.35
     pengh
    -0.35
     kund
    -0.35
     hard
    -0.35
     gradual
    -0.35
    POSITIVE LOGITS
     aim
    0.84
    target
    0.77
    aim
    0.75
     enjoy
    0.74
     purpose
    0.71
     target
    0.71
     surla
    0.68
    Purpose
    0.66
    PURPOSE
    0.66
    purpose
    0.64
    Activations Density 0.174%

    No Known Activations