© 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. 18-GEMMASCOPE-RES-16K
    11. 2718
    Prev
    Next
    INDEX
    Explanations

    discussions of research findings and implications based on observed data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    followed by "that"

    np_acts-logits-general · gemini-2.0-flash

    achieved or ensured conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 18-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_18/width_16k/average_l0_74
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.18.hook_resid_post
    Hook Layer
    18
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.83
    تقاوى
    -0.75
     فريبيس
    -0.75
     astray
    -0.73
    Lähteet
    -0.71
    ագրություններ
    -0.71
    relativeTime
    -0.69
     referrerpolicy
    -0.69
     ſche
    -0.68
     kasarigan
    -0.67
    POSITIVE LOGITS
     increased
    1.02
     an
    0.83
     a
    0.80
     continuous
    0.79
     continued
    0.77
     constant
    0.76
     consistent
    0.75
     greater
    0.74
     complete
    0.74
     significant
    0.74
    Activations Density 0.792%

    No Known Activations