© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 14448
    Prev
    Next
    INDEX
    Explanations

    code snippets and programming-related terminology

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

    File paths and directory names

    np_acts-logits-general · gemini-2.0-flash

    file paths and code delimiters

    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
     “
    -0.25
     the
    -0.23
     in
    -0.21
     ‘
    -0.21
     a
    -0.21
     van
    -0.21
     an
    -0.20
     K
    -0.20
     B
    -0.20
     of
    -0.20
    POSITIVE LOGITS
     avoient
    0.84
     feroit
    0.83
     auroit
    0.82
     varandra
    0.82
     étoient
    0.81
     enfans
    0.79
     pouvoit
    0.76
     étoit
    0.76
     stället
    0.75
     chrétiens
    0.74
    Activations Density 64.637%

    No Known Activations