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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 18-GEMMASCOPE-RES-16K
    11. 4822
    Prev
    Next
    INDEX
    Explanations

    terminology related to test case management and configuration settings

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

    software testing and test cases

    np_acts-logits-general · gemini-2.0-flash

    test cases and run

    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
     substitutes
    -0.58
    ReusableCell
    -0.56
     substitute
    -0.54
     sostitu
    -0.48
    handleRequest
    -0.48
     BoxFit
    -0.48
    Subs
    -0.48
    unmodifiable
    -0.46
    ADELPHIA
    -0.46
     remplace
    -0.46
    POSITIVE LOGITS
    évaluateur
    0.90
    gher
    0.69
     rerun
    0.68
     utafitiHapana
    0.68
     run
    0.67
     Execution
    0.67
     désolés
    0.66
     AssemblyCulture
    0.66
     execution
    0.64
     defe
    0.64
    Activations Density 0.273%

    No Known Activations