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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 1713
    Prev
    Next
    INDEX
    Explanations

    terms related to research, strategies, and frameworks in governance and health sectors

    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
     Italij
    -0.63
     Moscú
    -0.54
     Krakowie
    -0.53
     Füßen
    -0.46
     houſe
    -0.46
     Ersten
    -0.44
     própri
    -0.44
     katholischen
    -0.44
     Worten
    -0.44
     luzes
    -0.43
    POSITIVE LOGITS
     Expertise
    0.86
     Sensi
    0.82
     Awareness
    0.81
     Fac
    0.79
     Preparedness
    0.78
     Support
    0.77
     Compliance
    0.77
     Afford
    0.77
     Education
    0.76
     Efficiency
    0.76
    Activations Density 0.557%

    No Known Activations