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. 2277
    Prev
    Next
    INDEX
    Explanations

    specific timeframes and durations related to events or actions

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

    Number followed by "days" or a temperature

    np_acts-logits-general · gemini-2.0-flash

    numbers about time and quantity

    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
    tvguidetime
    -0.63
    неопр
    -0.61
    Autoritní
    -0.56
    IContainer
    -0.53
    Hochspringen
    -0.53
    DebuggerStep
    -0.52
     Савезне
    -0.52
    ساء
    -0.52
     AssemblyCulture
    -0.51
    nearly
    -0.51
    POSITIVE LOGITS
     ninety
    0.55
    fjspx
    0.54
    mybatisplus
    0.49
    avadoc
    0.47
    ModelBuilder
    0.47
     sixty
    0.46
    elcome
    0.45
    IVEREF
    0.44
     "..\..\..\
    0.44
    pylene
    0.44
    Activations Density 0.313%

    No Known Activations