© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 22-GEMMASCOPE-RES-16K
    11. 4825
    Prev
    Next
    INDEX
    Explanations

    information related to toxicity studies and safety evaluations for chemicals or materials

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

    toxicity

    np_acts-logits-general · gemini-2.0-flash

    chemical toxicity and safety hazards

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    jsxFileName
    -0.49
    TProtocol
    -0.42
    DECREF
    -0.41
    ija
    -0.41
     гла
    -0.40
     Lett
    -0.40
     TableColumn
    -0.40
    MockBean
    -0.39
    僧
    -0.39
    ularia
    -0.39
    POSITIVE LOGITS
     vPvB
    0.76
    principalTable
    0.69
     GHS
    0.68
     متعلقه
    0.68
    HMIS
    0.68
     Савезне
    0.68
     SDS
    0.67
     Anſ
    0.67
     MainAxisSize
    0.66
     Hazard
    0.66
    Activations Density 0.110%

    No Known Activations