© 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. 13710
    Prev
    Next
    INDEX
    Explanations

    specific terms related to medical and scientific topics

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

    ending in "-ary," "-arily," "-arin," or "-ory"

    np_acts-logits-general · gemini-2.0-flash

    words ending in ary or aries

    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
    ftagPool
    -0.60
    onAttach
    -0.53
    AndEndTag
    -0.47
    Xna
    -0.47
    afficheront
    -0.45
    InitVars
    -0.45
    PMailer
    -0.44
    ForTesting
    -0.44
     morada
    -0.43
    formación
    -0.42
    POSITIVE LOGITS
    ary
    1.33
    aries
    1.33
    ARY
    1.24
    ari
    1.23
    ars
    1.19
    aris
    1.18
    ar
    1.18
    AR
    1.15
    ARI
    1.14
    arie
    1.14
    Activations Density 0.417%

    No Known Activations