Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 12786
    Prev
    Next
    INDEX
    Explanations

    specific mathematical symbols or notations used in equations or expressions

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

    Mathematical notation involving parentheses/brackets and a variable "k"

    np_acts-logits-general · gemini-2.0-flash

    k following special characters

    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
     Kun
    -0.64
     Kart
    -0.61
    KEYCODE
    -0.59
    DotNetBar
    -0.58
     Kir
    -0.57
    enumi
    -0.57
     esternos
    -0.54
     للاسماء
    -0.54
     Kea
    -0.53
    migrationBuilder
    -0.53
    POSITIVE LOGITS
     k
    2.50
    k
    2.25
     к
    1.10
    k
    1.10
    к
    1.08
    𝑘
    0.95
     kk
    0.93
    kk
    0.87
     kink
    0.85
     kit
    0.83
    Activations Density 0.645%

    No Known Activations