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. 25-GEMMASCOPE-RES-16K
    6. 8518
    Prev
    Next
    INDEX
    Explanations

    frequent Japanese function words and grammatical markers

    oai_token-act-pair · o3-miniTriggered by @yemengyus1

    Japanese text, particularly expressions of emotion or reactions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kolorze
    -0.53
     szkole
    -0.50
    etheless
    -0.48
     UK
    -0.42
    brities
    -0.42
     trakcie
    -0.40
    igshid
    -0.38
     Polsce
    -0.38
     Apabila
    -0.38
    ťaž
    -0.38
    POSITIVE LOGITS
    rungsseite
    0.58
     poffible
    0.52
     neceffary
    0.51
    MigrationBuilder
    0.50
     McClure
    0.47
     Hickey
    0.46
     nemlig
    0.45
    товано
    0.45
     måte
    0.45
     McF
    0.45
    Activations Density 0.184%

    No Known Activations