© 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. 7672
    Prev
    Next
    INDEX
    Explanations

    references to locations and publishing details

    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
     laik
    -0.30
     physical
    -0.28
     cast
    -0.27
     fís
    -0.26
    Abstract
    -0.25
    fastjson
    -0.25
     fysis
    -0.24
    き
    -0.24
    DispatchToProps
    -0.24
    abstract
    -0.23
    POSITIVE LOGITS
     kaarangay
    0.73
     الرياضيه
    0.71
    oa̍t
    0.68
    enderror
    0.67
     onCreateView
    0.66
     EconPapers
    0.65
     Random
    0.65
    исленность
    0.63
     Italijanski
    0.63
    хьтан
    0.61
    Activations Density 0.306%

    No Known Activations