© 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. 24-GEMMASCOPE-RES-16K
    11. 2463
    Prev
    Next
    INDEX
    Explanations

    compound words or terms related to complex subjects

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

    Following "comp" or "Comp"

    np_acts-logits-general · gemini-2.0-flash

    words starting with comp

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Халык
    -0.51
    Discography
    -0.48
    GeoNames
    -0.48
    DeleteBehavior
    -0.46
    脚注の使い方
    -0.44
     éclat
    -0.44
     echi
    -0.43
    Mutagenicity
    -0.43
    split
    -0.41
    podob
    -0.41
    POSITIVE LOGITS
     betweenstory
    0.65
     saites
    0.61
    WireFormatLite
    0.59
    WithIOException
    0.58
    artment
    0.56
    acta
    0.55
    acts
    0.55
    tuer
    0.54
    enumi
    0.54
     pinulongan
    0.53
    Activations Density 0.153%

    No Known Activations