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. 40-GEMMASCOPE-RES-16K
    6. 5686
    Prev
    Next
    INDEX
    Explanations

    words and phrases that evoke strong emotional reactions or social issues

    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
    zaamheid
    -0.55
    новништво
    -0.55
     portability
    -0.54
    baarheid
    -0.54
    IBILITY
    -0.53
    IGENCE
    -0.53
    mindedness
    -0.53
     readiness
    -0.52
     Sensitivity
    -0.50
    reditation
    -0.50
    POSITIVE LOGITS
    acious
    0.73
    sterious
    0.70
    ultuous
    0.66
    itious
    0.64
    icious
    0.63
    oyant
    0.63
    orous
    0.62
    urious
    0.62
    isticated
    0.62
    arious
    0.61
    Activations Density 0.776%

    No Known Activations