© 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. 9460
    Prev
    Next
    INDEX
    Explanations

    references to specific key points or elements in structured data

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

    after "head", "key", "mid", or "free"

    np_acts-logits-general · gemini-2.0-flash

    Milton Freewater Dating chatbot

    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
     layui
    -0.74
    MENAFN
    -0.66
     segregated
    -0.61
     degradability
    -0.59
    ']))
    -0.59
    sfw
    -0.59
    iastes
    -0.58
     graders
    -0.58
    帖最后由
    -0.58
     evaluator
    -0.57
    POSITIVE LOGITS
    case
    0.52
    work
    0.47
    head
    0.47
    point
    0.46
    thing
    0.45
    place
    0.45
    book
    0.45
    ball
    0.43
    light
    0.42
    word
    0.41
    Activations Density 0.303%

    No Known Activations