© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13222
    Prev
    Next
    INDEX
    Explanations

    instances of ellipsis or continuation in text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     LUMP
    -0.72
     EconPapers
    -0.71
    ErrorListener
    -0.66
    ietic
    -0.65
    TagHelper
    -0.64
    OfBirth
    -0.63
    клопе
    -0.63
     Exactos
    -0.62
    parsedMessage
    -0.62
     useAppContext
    -0.61
    POSITIVE LOGITS
    /…
    0.78
    .…
    0.68
     contemporanea
    0.66
    "…
    0.64
    …,
    0.63
     …
    0.62
    Seguir
    0.59
    …
    0.59
    ,…
    0.58
    ?…
    0.58
    Activations Density 0.276%

    No Known Activations