© 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. 15-GEMMASCOPE-RES-16K
    6. 8826
    Prev
    Next
    INDEX
    Explanations

    references to statistical data or results, particularly involving comparisons or proportions

    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
    ItemBackground
    -0.73
     noqa
    -0.73
    jsonwebtoken
    -0.68
     createSlice
    -0.61
     portée
    -0.61
    Спасылкі
    -0.61
    CodedInputStream
    -0.59
     دیکھیے
    -0.55
    copyWith
    -0.54
     lenker
    -0.54
    POSITIVE LOGITS
     amongst
    0.62
     totalt
    0.57
    </caption>
    0.56
    ########.
    0.56
     parmi
    0.53
    among
    0.52
     sixteen
    0.52
     eighty
    0.52
     twelve
    0.52
    }/{
    0.51
    Activations Density 0.256%

    No Known Activations