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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 36-GEMMASCOPE-RES-16K
    6. 15869
    Prev
    Next
    INDEX
    Explanations

    concepts and terms related to health implications and changes in biological processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.57
    hyrchwyd
    -0.47
    Identyfik
    -0.44
    évaluateur
    -0.43
     disambiguazione
    -0.42
    Enllaces
    -0.42
    expandindo
    -0.42
    Bibliograf
    -0.42
     elongate
    -0.41
     resourceCulture
    -0.41
    POSITIVE LOGITS
     changes
    2.17
    changes
    1.85
     changements
    1.78
    Changes
    1.78
     Changes
    1.75
     cambios
    1.71
     perubahan
    1.66
     improvements
    1.65
     CHANGES
    1.58
     zmiany
    1.56
    Activations Density 1.689%

    No Known Activations