© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 9-GEMMASCOPE-RES-16K
    11. 9685
    Prev
    Next
    INDEX
    Explanations

    terms related to toxicity and irritation in substances

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

    descriptions of hazardous or toxic substances that can cause irritation, harm, or damage to human tissue or organs.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.69
     nakalista
    -0.60
     Wikimedijinoj
    -0.51
    mybatisplus
    -0.50
    TargetException
    -0.50
     utafitiHapana
    -0.50
    IsMutable
    -0.48
    rungsseite
    -0.46
     <<<<<<<<<<<<<<
    -0.45
     contextLoads
    -0.45
    POSITIVE LOGITS
     skin
    0.45
    Ecotoxicity
    0.40
    fullPath
    0.40
    towy
    0.39
     betweenstory
    0.38
     dried
    0.37
    skin
    0.37
     restricted
    0.37
     haw
    0.37
     Sinf
    0.37
    Activations Density 0.201%

    No Known Activations