© 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. 3-GEMMASCOPE-RES-16K
    6. 11313
    Prev
    Next
    INDEX
    Explanations

    expressions of contrast or transition in arguments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hauptartikel
    -0.65
    ctibles
    -0.63
     fowls
    -0.61
    công
    -0.60
     confronti
    -0.60
    ıdır
    -0.60
     ANCHE
    -0.59
    Incon
    -0.58
    itespace
    -0.58
    tualmente
    -0.58
    POSITIVE LOGITS
     así
    1.46
     так
    1.41
     così
    1.38
     så
    1.31
     assim
    1.26
    Так
    1.17
     Так
    1.17
     tak
    1.14
     so
    1.10
     näin
    1.07
    Activations Density 0.152%

    No Known Activations