© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3015
    Prev
    Next
    INDEX
    Explanations

    items related to mathematical summation and limits

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

    Mathematical sums or summations

    np_acts-logits-general · gemini-2.0-flash

    mathematical sums

    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
    RetentionPolicy
    -0.98
    tvguidetime
    -0.97
     متعلقه
    -0.90
     تضيفلها
    -0.86
    enderror
    -0.85
     itſelf
    -0.84
    GraphicsUnit
    -0.83
    Lähteet
    -0.83
     Jefus
    -0.83
     contextLoads
    -0.83
    POSITIVE LOGITS
    limits
    0.74
    limit
    0.52
    从
    0.50
    _{
    0.50
     from
    0.49
     nor
    0.49
     limit
    0.48
     From
    0.46
    nor
    0.46
    _{\
    0.45
    Activations Density 0.419%

    No Known Activations