© 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. 24-GEMMASCOPE-RES-16K
    6. 4217
    Prev
    Next
    INDEX
    Explanations

    key individuals and their roles or contributions in various contexts

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

    Follows pronouns, conjunctions, and symbols

    np_acts-logits-general · gemini-2.0-flash

    actions after common words

    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
     виправивши
    -0.68
     looms
    -0.62
     mourut
    -0.60
     pouvoit
    -0.58
    OrBuilder
    -0.57
    enschappelijke
    -0.57
     allait
    -0.57
     expires
    -0.56
     isn
    -0.56
     avoient
    -0.55
    POSITIVE LOGITS
     designs
    0.76
    kloped
    0.73
    PerformLayout
    0.73
     advocates
    0.69
     tail
    0.68
     researches
    0.66
     devis
    0.64
     mentors
    0.64
     studies
    0.63
     champions
    0.61
    Activations Density 0.237%

    No Known Activations