© 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
    7. Residual Stream - 16k
    9. 30-GEMMASCOPE-RES-16K
    11. 8910
    Prev
    Next
    INDEX
    Explanations

    lines of code or programming constructs

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

    Code-related terms and identifiers

    np_acts-logits-general · gemini-2.0-flash

    technical terms and foreign words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 30-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_30/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.30.hook_resid_post
    Hook Layer
    30
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     parseFrom
    -0.31
     Gerechtigkeit
    -0.28
    本
    -0.26
    du
    -0.26
     toneladas
    -0.25
    แบบ
    -0.25
     podrá
    -0.25
     Privacidade
    -0.24
     Erklärung
    -0.24
     sienta
    -0.24
    POSITIVE LOGITS
     queſta
    0.75
     laſſen
    0.70
     pinulongan
    0.68
    ſchaft
    0.66
     CreateTagHelper
    0.66
    rungsseite
    0.63
     müſſen
    0.63
    ロウィン
    0.62
     nahilalakip
    0.62
    iſen
    0.61
    Activations Density 0.060%

    No Known Activations