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. 24-GEMMASCOPE-RES-16K
    6. 4382
    Prev
    Next
    INDEX
    Explanations

    mathematical terms and symbols related to expressions and operations

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

    Indices, often single letters like i, j, k

    np_acts-logits-general · gemini-2.0-flash

    indices followed by i, j, or 1

    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
    
    -0.55
    Portail
    -0.55
    InputBorder
    -0.55
     Мексичка
    -0.55
    sizeCache
    -0.54
     للاسماء
    -0.53
    textwidth
    -0.53
     +%
    -0.53
    govine
    -0.53
    ORAGE
    -0.53
    POSITIVE LOGITS
     i
    0.97
    j
    0.94
    i
    0.92
     j
    0.92
    k
    0.66
    𝑖
    0.65
     k
    0.65
     ith
    0.63
     ij
    0.63
    jei
    0.62
    Activations Density 1.568%

    No Known Activations