Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 4881
    Prev
    Next
    INDEX
    Explanations

    concepts related to realism and practical applications in various contexts

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

    preceding "real" or variants of "real"

    np_acts-logits-general · gemini-2.0-flash

    contrasting practice and real

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.73
    yntaxException
    -0.70
    XmlType
    -0.61
    ArrowToggle
    -0.58
    aronder
    -0.56
     GenerationType
    -0.55
    tonode
    -0.54
    testens
    -0.52
    IndentedString
    -0.51
    tableFuture
    -0.51
    POSITIVE LOGITS
     real
    3.36
    real
    2.94
     REAL
    2.62
     actual
    2.60
    Real
    2.53
     réel
    2.51
     reale
    2.50
    REAL
    2.49
     реаль
    2.49
     reales
    2.48
    Activations Density 1.001%

    No Known Activations