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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 4162
    Prev
    Next
    INDEX
    Explanations

    technical terms and concepts related to programming and software development

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

    after a class name/type

    np_acts-logits-general · gemini-2.0-flash

    programming constructs

    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
     do
    -0.71
     in
    -0.69
     cost
    -0.68
    -
    -0.67
     file
    -0.66
     v
    -0.66
     un
    -0.66
     and
    -0.64
    .
    -0.64
     are
    -0.64
    POSITIVE LOGITS
     larmes
    0.93
     avoient
    0.90
     brancas
    0.88
     vermelhas
    0.86
     étoient
    0.85
     colorés
    0.84
     chré
    0.83
     jouets
    0.81
     Houſe
    0.80
     enfans
    0.80
    Activations Density 0.196%

    No Known Activations