© 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. 4071
    Prev
    Next
    INDEX
    Explanations

    references to software packages and their sources, particularly from GitHub

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

    "package" or "Category"

    np_acts-logits-general · gemini-2.0-flash

    github paths, categories, built places

    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
    LookAnd
    -0.76
    principalColumn
    -0.74
    queryInterface
    -0.73
     <>",
    -0.71
    PreferredItem
    -0.71
    AsUp
    -0.68
    addCriterion
    -0.64
     !”
    -0.61
    InitVars
    -0.60
    parsedMessage
    -0.60
    POSITIVE LOGITS
    package
    0.57
    Спољашње
    0.55
     venons
    0.51
    assets
    0.48
     yw
    0.48
     протя
    0.48
     pkg
    0.48
    íř
    0.47
    http
    0.46
     vle
    0.46
    Activations Density 0.016%

    No Known Activations