© 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. 24-GEMMASCOPE-RES-16K
    11. 4746
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and expressions related to sequences and convergence

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

    Mathematical convergence

    np_acts-logits-general · gemini-2.0-flash

    convergence and limits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    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
    -0.73
     CURIAM
    -0.62
    TagHelper
    -0.60
     Pry
    -0.59
     Antif
    -0.58
     незавершена
    -0.56
    SerializeField
    -0.55
    ernalia
    -0.55
    TagMode
    -0.54
     SqlDbType
    -0.54
    POSITIVE LOGITS
     limit
    1.05
     converges
    0.99
     convergence
    0.94
    Limit
    0.94
     lim
    0.93
     convergent
    0.92
     Limit
    0.92
    lim
    0.91
    conver
    0.91
    limit
    0.90
    Activations Density 1.734%

    No Known Activations