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. 2339
    Prev
    Next
    INDEX
    Explanations

    punctuations and decimal points

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

    Numbers with decimals

    np_acts-logits-general · gemini-2.0-flash

    numerical measurements and data

    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
    .
    -0.60
    EndContext
    -0.54
    .,
    -0.47
     שוליים
    -0.46
    bouncycastle
    -0.45
    ்த்த
    -0.45
    ers
    -0.45
    CDCl
    -0.44
     Allociné
    -0.43
    tions
    -0.43
    POSITIVE LOGITS
    fromnode
    0.71
    новниш
    0.69
    Filmografie
    0.67
    Geografi
    0.65
    couvrez
    0.62
    RenderAtEndOf
    0.62
     ErrIntOverflow
    0.62
    indd
    0.61
    存于互联网档案馆
    0.60
     समीक्षक
    0.60
    Activations Density 0.468%

    No Known Activations