© 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. 40-GEMMASCOPE-RES-16K
    6. 6148
    Prev
    Next
    INDEX
    Explanations

    phrases indicating urgency or necessity related to protection or safety

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     BoxFit
    -0.46
     تضيفلها
    -0.42
    Kariera
    -0.40
     nahilalakip
    -0.38
    :✨
    -0.37
     CreateTagHelper
    -0.35
     snippetHide
    -0.35
    kuuta
    -0.34
     transférez
    -0.33
     مشين
    -0.32
    POSITIVE LOGITS
     cost
    3.86
    cost
    3.38
     costs
    3.27
    Cost
    3.20
     Cost
    3.20
     COST
    2.95
    COST
    2.88
     Costs
    2.84
    costs
    2.83
    Costs
    2.73
    Activations Density 1.276%

    No Known Activations