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. 16-GEMMASCOPE-RES-16K
    6. 3208
    Prev
    Next
    INDEX
    Explanations

    acronyms and abbreviations related to scientific terms and measures

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

    Often comes before seemingly random characters/letters

    np_acts-logits-general · gemini-2.0-flash

    section or derivative markers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    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
    -1.08
     ProtoMessage
    -1.07
    ValueStyle
    -1.05
     Chwiliwch
    -1.02
    MessageOf
    -1.01
     nahilalakip
    -0.98
     initComponents
    -0.98
     للاسماء
    -0.97
     ***!
    -0.96
     '\\;'
    -0.96
    POSITIVE LOGITS
    ™.
    0.52
    <bos>
    0.48
    ↵↵
    0.45
    ®.
    0.45
    !
    0.41
    $.
    0.41
    <>(
    0.41
    $\
    0.40
    tra
    0.40
    B
    0.37
    Activations Density 0.816%

    No Known Activations