© 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. 16108
    Prev
    Next
    INDEX
    Explanations

    terms related to environmental contamination and health risks associated with poisoning

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

    Toxins, poisons, contamination

    np_acts-logits-general · gemini-2.0-flash

    toxic substances and contamination

    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
    stateProvider
    -0.60
    Datuak
    -0.57
     otim
    -0.55
     تضيفلها
    -0.55
    makedirs
    -0.50
    VIAF
    -0.50
    principalTable
    -0.47
    assword
    -0.46
    beforeSend
    -0.45
     desmotiv
    -0.45
    POSITIVE LOGITS
     poisoning
    1.50
     toxic
    1.49
     poisonous
    1.44
     poison
    1.34
     toxins
    1.34
     toxicity
    1.32
     poisoned
    1.32
     poisons
    1.32
    poison
    1.29
     Toxic
    1.23
    Activations Density 0.434%

    No Known Activations