© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 15707
    Prev
    Next
    INDEX
    Explanations

    terms and concepts associated with material properties and structures in physics

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

    before chemical elements or materials

    np_acts-logits-general · gemini-2.0-flash

    biological materials and semiconductors

    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
    .*")]
    -0.71
    awaiter
    -0.57
    strix
    -0.55
    Cyfeiriadau
    -0.55
     desapar
    -0.54
     createState
    -0.52
    ropractor
    -0.52
    احث
    -0.51
    "])){
    -0.51
     ویکی‌آمباردا
    -0.51
    POSITIVE LOGITS
     organic
    0.68
     proteins
    0.68
     solids
    0.67
     biological
    0.66
     organics
    0.64
    InitVars
    0.57
     biolog
    0.56
    biological
    0.55
    ISupport
    0.55
     semiconductors
    0.55
    Activations Density 1.169%

    No Known Activations