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. 24-GEMMASCOPE-RES-16K
    6. 8318
    Prev
    Next
    INDEX
    Explanations

    references to communist ideologies and related political movements

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

    before certain suffixes (ica, tics, ve)

    np_acts-logits-general · gemini-2.0-flash

    communauté, mathématique, météorologique, comique

    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
     she
    -0.50
    ElementException
    -0.49
     whole
    -0.44
    ilyn
    -0.44
    mètre
    -0.44
     Passing
    -0.43
    Trả
    -0.43
    #+#
    -0.42
    eventbus
    -0.42
    ˌ
    -0.40
    POSITIVE LOGITS
     estekak
    0.72
    хьтан
    0.69
    modelBuilder
    0.62
     مرئيه
    0.61
     CURIAM
    0.59
     Akismet
    0.59
    VersionUID
    0.59
    uxxxx
    0.56
     EconPapers
    0.56
    anglicky
    0.55
    Activations Density 0.116%

    No Known Activations