© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 24-GEMMASCOPE-RES-16K
    11. 4994
    Prev
    Next
    INDEX
    Explanations

    mentions of corporate commitments to social responsibility

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Business-related and social responsibility concepts

    np_acts-logits-general · gemini-2.0-flash

    corporate social responsibility partnerships

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    iteten
    -0.39
    doria
    -0.39
     geometry
    -0.39
     Bacteriol
    -0.38
    Passcode
    -0.38
    êtement
    -0.38
     arreglos
    -0.38
    Спољашње
    -0.37
    igkeit
    -0.37
     záz
    -0.37
    POSITIVE LOGITS
    communities
    0.55
     communities
    0.52
     philanthropic
    0.51
     philanthropy
    0.51
     partnerships
    0.50
     Corporate
    0.49
    supporting
    0.48
    community
    0.47
    sustainability
    0.47
     corporate
    0.47
    Activations Density 0.143%

    No Known Activations