Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 4421
    Prev
    Next
    INDEX
    Explanations

    chemical processes and synthesis related to nanoparticles

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

    Organic solvents

    np_acts-logits-general · gemini-2.0-flash

    organic solvents

    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
    UnsafeEnabled
    -0.65
     Claudius
    -0.63
    AccessorTable
    -0.61
    ElementException
    -0.60
     للمعارف
    -0.57
    tvguidetime
    -0.57
    XmlEnum
    -0.56
    databind
    -0.54
    setVerticalGroup
    -0.54
    RenderAtEndOf
    -0.52
    POSITIVE LOGITS
     ethanol
    0.81
     methanol
    0.81
     acetone
    0.78
     solvents
    0.77
     solvent
    0.75
     chloroform
    0.74
     Ethanol
    0.73
     Solvent
    0.71
     Methanol
    0.70
     aceton
    0.69
    Activations Density 0.605%

    No Known Activations