© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 30-GEMMASCOPE-RES-16K
    6. 10899
    Prev
    Next
    INDEX
    Explanations

    code-related keywords and error messages in programming environments

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

    File paths or URLs with brackets and parentheses

    np_acts-logits-general · gemini-2.0-flash

    image links, citations, or code paths

    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
    Portail
    -0.42
    MockBean
    -0.40
    isk
    -0.37
    IntoConstraints
    -0.36
    ConstraintMaker
    -0.34
    oredCriteria
    -0.32
    ParallelGroup
    -0.31
     Scissors
    -0.31
    Insee
    -0.31
     CanadaChoose
    -0.30
    POSITIVE LOGITS
    ../
    1.14
    ../../
    1.08
     ../
    1.06
    ../../../
    1.02
     ./
    0.96
     ../../
    0.94
    ./
    0.89
     "./
    0.88
     ~/
    0.88
     "../
    0.87
    Activations Density 0.541%

    No Known Activations