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. 10528
    Prev
    Next
    INDEX
    Explanations

    the word "First" followed by numbers or steps indicating order or sequence

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

    Preceding ordinal indicators

    np_acts-logits-general · gemini-2.0-flash

    beginning a list with first

    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
    Vidite
    -0.82
     alfo
    -0.79
     Winaray
    -0.74
    migrationBuilder
    -0.73
     myſelf
    -0.72
     tfsi
    -0.71
     Shakspeare
    -0.70
     später
    -0.68
     afterwards
    -0.66
     vuitton
    -0.66
    POSITIVE LOGITS
     is
    0.68
     let
    0.67
     thing
    0.67
     off
    0.66
     lets
    0.61
     اینکه
    0.61
     of
    0.57
    arily
    0.57
     we
    0.57
    èrement
    0.55
    Activations Density 0.175%

    No Known Activations