Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 3355
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to methodology and analysis in research studies

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

    Preceding words related to scientific studies

    np_acts-logits-general · gemini-2.0-flash

    stability, validity, association, correlation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.76
    __*/
    -0.73
    twimg
    -0.73
    usercontent
    -0.71
     يتيمه
    -0.71
     ſmall
    -0.71
     GenerationType
    -0.71
     NSCoder
    -0.71
    expandindo
    -0.71
    LookAnd
    -0.70
    POSITIVE LOGITS
     study
    0.77
     analysis
    0.73
     Study
    0.67
     relation
    0.63
    Study
    0.63
     studie
    0.60
     STUDY
    0.60
     relative
    0.60
     studies
    0.59
     Analysis
    0.56
    Activations Density 1.222%

    No Known Activations