Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 7562
    Prev
    Next
    INDEX
    Explanations

    language related to caution and safety measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    MessageTagHelper
    -0.65
     للمعارف
    -0.58
     يتيمه
    -0.53
     ModelExpression
    -0.53
    
    -0.49
     contextLoads
    -0.43
     esternos
    -0.41
     intr
    -0.40
    pośred
    -0.40
    delwed
    -0.40
    POSITIVE LOGITS
     precaution
    0.82
     precautionary
    0.79
     cautious
    0.76
     precau
    0.69
     precautions
    0.63
     safeguard
    0.60
    Precautionary
    0.59
     safest
    0.59
     safer
    0.59
    Precautions
    0.58
    Activations Density 0.414%

    No Known Activations