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. 14757
    Prev
    Next
    INDEX
    Explanations

    structured data regarding attributes and classifications

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

    Items in a series or group

    np_acts-logits-general · gemini-2.0-flash

    quantifying discrete items

    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
     few
    -0.62
    everywhere
    -0.60
    writeFieldEnd
    -0.59
     everywhere
    -0.59
    ')['
    -0.57
     многих
    -0.56
    之类的
    -0.55
    Everywhere
    -0.55
     FEW
    -0.55
    URLException
    -0.54
    POSITIVE LOGITS
     apiece
    1.32
     plus
    1.16
     each
    1.15
     totaling
    1.14
     namely
    1.12
     total
    1.08
     totalling
    1.07
     totalt
    1.04
    each
    1.03
    total
    1.02
    Activations Density 0.684%

    No Known Activations