© 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. 8321
    Prev
    Next
    INDEX
    Explanations

    terms related to additional or surplus medical features or conditions

    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
     CommandType
    -0.65
    Pues
    -0.62
    Naissance
    -0.62
    browserify
    -0.61
     IMS
    -0.61
     Barbosa
    -0.59
     oiseaux
    -0.58
    )."
    -0.57
    tidaknya
    -0.57
     censura
    -0.57
    POSITIVE LOGITS
     Extra
    1.47
     EXTRA
    1.47
     extra
    1.41
    Extra
    1.38
    extra
    1.30
    EXTRA
    1.21
     Extras
    1.18
    extras
    1.11
     EXTR
    1.11
    xtra
    1.08
    Activations Density 0.186%

    No Known Activations