© 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. 12166
    Prev
    Next
    INDEX
    Explanations

    words associated with scientific and technical concepts, particularly in medical and engineering contexts

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

    ending in "or," "and," "with" and similar conjunctions

    np_acts-logits-general · gemini-2.0-flash

    legalistic terms and specific jargon

    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
     t
    -0.91
     tee
    -0.76
     tees
    -0.74
    T
    -0.73
    t
    -0.71
    getT
    -0.70
     torus
    -0.70
     tg
    -0.68
     т
    -0.68
     tc
    -0.68
    POSITIVE LOGITS
    SharedDtor
    0.55
    afficheront
    0.46
    ⓧ
    0.39
    unnitel
    0.38
     Wikimedijinoj
    0.37
    boutin
    0.36
    Autoritní
    0.35
    wki
    0.35
     <<<<<<<<<<<<<<
    0.34
    oare
    0.34
    Activations Density 1.727%

    No Known Activations