© 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. 8732
    Prev
    Next
    INDEX
    Explanations

    discussions about ideas and their origins or ownership

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

    Preceding tokens of "idea"

    np_acts-logits-general · gemini-2.0-flash

    ideas and suggestions

    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
    enderror
    -0.61
    getColumnIndex
    -0.61
    Clik
    -0.57
    RenderAtEndOf
    -0.55
    Autoritní
    -0.53
    ⎨
    -0.53
    ensement
    -0.52
    "]));
    -0.52
    nologue
    -0.52
     defaultstate
    -0.52
    POSITIVE LOGITS
     idea
    3.15
     ideas
    3.09
     Ideas
    2.65
     Idea
    2.65
    idea
    2.55
    Idea
    2.53
    Ideas
    2.51
    ideas
    2.48
     idee
    2.46
     idée
    2.42
    Activations Density 0.396%

    No Known Activations