© 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. 19-GEMMASCOPE-RES-16K
    6. 4893
    Prev
    Next
    INDEX
    Explanations

    terms related to scientific research and interdisciplinary collaboration

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 19-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_19/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Hook Layer
    19
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.67
    RenderAtEndOf
    -0.61
    IVEREF
    -0.59
    AndEndTag
    -0.53
    GetAsync
    -0.53
     oprot
    -0.52
    makeConstraints
    -0.52
    Obrázky
    -0.50
    vikling
    -0.50
    fated
    -0.50
    POSITIVE LOGITS
     experience
    2.33
    experience
    2.02
     Experience
    1.96
    Experience
    1.93
     EXPERIENCE
    1.86
     expertise
    1.85
     experienced
    1.72
     expérience
    1.70
     experiencia
    1.68
    EXPERIENCE
    1.66
    Activations Density 0.416%

    No Known Activations