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. 23-GEMMASCOPE-RES-16K
    6. 6372
    Prev
    Next
    INDEX
    Explanations

    mentions of harmful substances and dietary restrictions related to health

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Eigent
    -0.46
    térature
    -0.44
    分散
    -0.43
    numerusform
    -0.42
     Daten
    -0.42
    apnews
    -0.41
     Himo
    -0.40
     dilan
    -0.40
    enegal
    -0.40
     Murders
    -0.40
    POSITIVE LOGITS
     chemicals
    1.24
     pesticides
    1.09
     toxins
    1.07
     artificial
    1.07
     chemical
    1.06
     preservatives
    1.05
     Chemicals
    1.04
     harmful
    1.02
     toxic
    1.02
     additives
    0.99
    Activations Density 0.223%

    No Known Activations