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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    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. 12242
    Prev
    Next
    INDEX
    Explanations

    structures related to code and data representation

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

    Code indices

    np_acts-logits-general · gemini-2.0-flash

    code indices

    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
     CreateTagHelper
    -0.60
    SourceChecksum
    -0.53
     Hod
    -0.52
     Germain
    -0.52
    昆
    -0.50
    nep
    -0.48
     ph
    -0.48
     ویکی‌پدیای
    -0.47
     Himo
    -0.47
     perse
    -0.47
    POSITIVE LOGITS
     idx
    1.24
    idx
    1.18
    Idx
    1.04
    IDX
    1.00
     lbl
    0.83
     Cabral
    0.82
     srv
    0.82
     yrs
    0.82
     txt
    0.81
     Cllr
    0.80
    Activations Density 0.252%

    No Known Activations