© 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. 3-GEMMASCOPE-RES-16K
    11. 5924
    Prev
    Next
    INDEX
    Explanations

    punctuation and conjunctions that suggest continuation or connection in thoughts

    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
    HandlerContext
    -0.67
    )__
    -0.63
    ocities
    -0.61
    gonic
    -0.61
     iconFacebook
    -0.59
     Barr
    -0.53
    ImageContext
    -0.52
     кстати
    -0.52
    쉰
    -0.52
    HostException
    -0.52
    POSITIVE LOGITS
     Pingback
    0.53
     Bourgoin
    0.52
     Insee
    0.48
    InjectAttribute
    0.47
     Accesat
    0.46
    虫
    0.43
     Normdatei
    0.42
     Sciento
    0.41
    Referințe
    0.40
    thyst
    0.40
    Activations Density 0.575%

    No Known Activations