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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 2-GEMMASCOPE-RES-16K
    11. 1705
    Prev
    Next
    INDEX
    Explanations

    references to the human species and human-related topics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     accompany
    -0.63
     accompanies
    -0.59
     accompanying
    -0.53
     accompanied
    -0.53
    accompag
    -0.46
     already
    -0.46
    already
    -0.45
    accompanied
    -0.45
    PropertyChanging
    -0.45
     accompaniment
    -0.44
    POSITIVE LOGITS
     human
    2.14
    Human
    1.91
    human
    1.90
     Human
    1.88
     HUMAN
    1.70
     humans
    1.67
    HUMAN
    1.64
     humano
    1.52
     Humans
    1.48
    Humans
    1.45
    Activations Density 0.078%

    No Known Activations