© 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. 1987
    Prev
    Next
    INDEX
    Explanations

    underscores followed by the letter 't'

    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
    ναι
    -0.64
    |')
    -0.50
     eventdata
    -0.48
     mergeFrom
    -0.48
    nejšie
    -0.47
    </td>
    -0.46
    using
    -0.45
     Cruces
    -0.45
    話す
    -0.44
     maga
    -0.44
    POSITIVE LOGITS
    styleType
    0.81
    TagMode
    0.77
    enumii
    0.76
    onViewCreated
    0.72
    󠁿
    0.68
    MessageOf
    0.68
     itemId
    0.66
    EndContext
    0.64
    enumi
    0.63
     disambiguazione
    0.63
    Activations Density 0.121%

    No Known Activations