© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 6494
    Prev
    Next
    INDEX
    Explanations

    hexadecimal and numerical data

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

    Hexadecimal values and numbers

    np_acts-logits-general · gemini-2.0-flash

    numbers and words like `finds` or `part`

    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
    NOPQRST
    -0.53
    ArgumentParser
    -0.52
    igshid
    -0.47
    ERÍA
    -0.46
    numerusform
    -0.43
    IntoConstraints
    -0.41
     المعيارى
    -0.40
    ÁND
    -0.40
    itorial
    -0.40
    IsContent
    -0.39
    POSITIVE LOGITS
    9
    1.37
    4
    1.36
    5
    1.35
    8
    1.35
    3
    1.34
    7
    1.33
    6
    1.33
    1
    1.30
    2
    1.29
    0
    1.25
    Activations Density 0.319%

    No Known Activations