© 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. 352
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" used in various contexts

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

    Code snippets containing "import" and "session"

    np_acts-logits-general · gemini-2.0-flash

    as K or T

    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
    PhysRev
    -0.68
    PhysRevD
    -0.68
     GenerationType
    -0.66
    Халык
    -0.57
     FileReader
    -0.56
    Witam
    -0.55
    WebElementEntity
    -0.54
     jScrollPane
    -0.54
    +"'
    -0.54
     iconst
    -0.52
    POSITIVE LOGITS
    الإنجليزية
    0.64
    enumi
    0.62
    phem
    0.58
     lenker
    0.56
    Personensuche
    0.55
    ximity
    0.54
    ISHOP
    0.54
    principalTable
    0.53
    ÉN
    0.53
    ageo
    0.53
    Activations Density 0.025%

    No Known Activations