© 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. 8891
    Prev
    Next
    INDEX
    Explanations

    logging and error handling functions in code

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

    Code-related terms and error handling

    np_acts-logits-general · gemini-2.0-flash

    `Fatal` error handling

    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
     nakalista
    -0.56
     Tal
    -0.39
    исленность
    -0.39
    UnusedPrivate
    -0.39
    hoedd
    -0.36
     Talbot
    -0.36
    MarshalTo
    -0.36
    setVerticalGroup
    -0.35
    ましい
    -0.35
    Obrázky
    -0.35
    POSITIVE LOGITS
    UrlResolution
    0.62
     surla
    0.55
    ſelf
    0.53
    ulemon
    0.52
     BrowserModule
    0.51
    Toponymie
    0.49
    ajuato
    0.48
    balleur
    0.47
     ProtoMessage
    0.45
     فريبيس
    0.44
    Activations Density 0.219%

    No Known Activations