© 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-2-2B
    4. Residual Stream - 16k
    5. 18-GEMMASCOPE-RES-16K
    6. 6007
    Prev
    Next
    INDEX
    Explanations

    terms related to errors, defects, and issues in various contexts

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

    Errors, defects, and issues

    np_acts-logits-general · gemini-2.0-flash

    errors and defects occurred

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     fas
    -0.45
    <?>
    -0.45
    ipedi
    -0.44
     sbag
    -0.42
     pad
    -0.42
     murdered
    -0.41
    tivamente
    -0.41
    lais
    -0.41
    UpdatedBy
    -0.41
    kins
    -0.39
    POSITIVE LOGITS
     occurred
    1.22
     occurring
    1.15
     caused
    1.14
     occured
    1.14
     occur
    1.09
     occurs
    1.06
    occur
    1.01
     Caused
    0.99
     Occur
    0.98
     affecting
    0.98
    Activations Density 1.343%

    No Known Activations