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. 15233
    Prev
    Next
    INDEX
    Explanations

    quantitative measurements related to medical or scientific data

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

    Quantity or level of something

    np_acts-logits-general · gemini-2.0-flash

    amounts and rates

    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
     '-';
    -0.58
    npmjs
    -0.58
    ,‎
    -0.57
    Rohy
    -0.57
     EconPapers
    -0.56
    Ủ
    -0.55
    WindowConstants
    -0.55
    Hochspringen
    -0.54
    ześnie
    -0.54
     bezeichneter
    -0.53
    POSITIVE LOGITS
     totaling
    1.20
     ranging
    1.20
     amounting
    1.18
     totalling
    1.12
     equal
    1.00
     exceeding
    0.92
     equivalent
    0.92
     numbering
    0.88
     averaging
    0.86
     sebesar
    0.86
    Activations Density 0.507%

    No Known Activations