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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 18-GEMMASCOPE-RES-16K
    6. 8670
    Prev
    Next
    INDEX
    Explanations

    references to inclusion and integration in various contexts

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

    followed by prepositions like "into" or "in"

    np_acts-logits-general · gemini-2.0-flash

    inclusion or placement

    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
    -1.16
     disambiguazione
    -0.84
     كومونز
    -0.79
     Efq
    -0.79
    enderror
    -0.78
     lenker
    -0.76
    saraba
    -0.75
    OGND
    -0.74
    GTCX
    -0.72
    DebuggerNonUser
    -0.70
    POSITIVE LOGITS
     into
    1.03
     among
    0.95
     dalam
    0.92
    among
    0.87
     in
    0.81
     nelle
    0.79
     amongst
    0.79
     nella
    0.76
     trong
    0.75
     inclusion
    0.71
    Activations Density 0.676%

    No Known Activations