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. 10721
    Prev
    Next
    INDEX
    Explanations

    actions of bringing or delivering significant outcomes or changes

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

    "bring" and its inflections

    np_acts-logits-general · gemini-2.0-flash

    bring about, meaning, it, forth

    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
    tagHelper
    -0.64
    existsSync
    -0.63
     Bourgoin
    -0.60
    idemiology
    -0.59
    
    -0.58
    AtIndexPath
    -0.57
    usercontent
    -0.57
     FishBase
    -0.57
    wnież
    -0.56
    enegal
    -0.56
    POSITIVE LOGITS
    Bring
    1.46
     Bring
    1.41
     brought
    1.38
     bring
    1.38
     brings
    1.31
    Bringing
    1.29
     BRING
    1.27
     forth
    1.27
     Bringing
    1.26
     bringing
    1.25
    Activations Density 0.053%

    No Known Activations