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. 13017
    Prev
    Next
    INDEX
    Explanations

    parentheses and their usages in code or mathematical expressions

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

    Opening parentheses followed by other characters

    np_acts-logits-general · gemini-2.0-flash

    purpose, pleasure, Majesty

    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
    -
    -0.97
    ,
    -0.91
    .
    -0.89
    :
    -0.85
    /
    -0.83
     O
    -0.77
    $
    -0.75
     ins
    -0.75
     das
    -0.74
     van
    -0.74
    POSITIVE LOGITS
     purpoſe
    1.33
     reaſon
    1.30
     pleaſure
    1.30
     myſelf
    1.30
     occaf
    1.26
     itſelf
    1.26
     greateſt
    1.25
     poffible
    1.24
     Majefty
    1.22
     themſelves
    1.22
    Activations Density 1.134%

    No Known Activations