© 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-2-9B
    4. Residual Stream - 16k
    5. 38-GEMMASCOPE-RES-16K
    6. 8205
    Prev
    Next
    INDEX
    Explanations

    phrases related to concerns about safety and effectiveness in parenting and childcare products

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 38-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_38/width_16k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.38.hook_resid_post
    Hook Layer
    38
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ilustracja
    -0.82
     dezelve
    -0.67
     miniaturka
    -0.62
    occasione
    -0.62
     يتيمه
    -0.61
     ilustracji
    -0.60
     valentín
    -0.58
     indígen
    -0.56
    LEGGI
    -0.56
    Spolja
    -0.53
    POSITIVE LOGITS
     lol
    1.11
     IMO
    1.05
     imo
    1.02
     IIRC
    1.01
     tbh
    0.99
     haha
    0.99
     iirc
    0.96
    ...
    0.93
     IMHO
    0.90
     w
    0.90
    Activations Density 1.601%

    No Known Activations