© 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. 15-GEMMASCOPE-RES-16K
    11. 2555
    Prev
    Next
    INDEX
    Explanations

    the presence of a document's structural elements, such as the beginning of a new section or title

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Efq
    -0.79
     Reſ
    -0.76
     Diſ
    -0.75
     Majefty
    -0.70
     Anſ
    -0.70
     Conſ
    -0.69
     Verſ
    -0.68
     iſt
    -0.65
     moschino
    -0.63
     againſt
    -0.63
    POSITIVE LOGITS
    <eos>
    0.69
    帖最后由
    0.65
    AndEndTag
    0.61
    Przypisy
    0.56
    DebuggerStep
    0.56
    </thead>
    0.52
    APOLIS
    0.52
    StoreMessageInfo
    0.51
     Wicidata
    0.48
     disambiguazione
    0.48
    Activations Density 0.085%

    No Known Activations