© 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. 39-GEMMASCOPE-RES-16K
    11. 1021
    Prev
    Next
    INDEX
    Explanations

    phrases related to comparative analysis or evaluation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hasard
    -0.35
     statt
    -0.35
    instead
    -0.34
    pholes
    -0.34
     instead
    -0.34
     поддержку
    -0.33
     cesse
    -0.32
     yhte
    -0.32
     inoltre
    -0.31
    lored
    -0.30
    POSITIVE LOGITS
     terms
    2.14
    terms
    1.69
     TERMS
    1.40
     regards
    1.35
    Terms
    1.34
     Terms
    1.30
     termes
    1.29
     términos
    1.28
     regard
    1.22
    TERMS
    1.21
    Activations Density 0.628%

    No Known Activations