© 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. 3021
    Prev
    Next
    INDEX
    Explanations

    terms related to predictions and evaluations of outcomes or success

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

    Followed by "shape", "work", or similar verbs

    np_acts-logits-general · gemini-2.0-flash

    how things turn out

    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
     pinulongan
    -0.69
     curie
    -0.51
     муніципалі
    -0.47
    :✨
    -0.47
    kadang
    -0.45
    *{-
    -0.45
    accompanied
    -0.43
     newBuilder
    -0.43
    reliance
    -0.42
    ModelAttribute
    -0.42
    POSITIVE LOGITS
     pans
    1.03
     panning
    1.01
     pan
    0.96
    pan
    0.74
    anned
    0.73
    pans
    0.73
     Pans
    0.67
     worked
    0.65
    Rüyada
    0.65
     Pan
    0.65
    Activations Density 0.289%

    No Known Activations