© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 40-GEMMASCOPE-RES-16K
    11. 2064
    Prev
    Next
    INDEX
    Explanations

    phrases related to obstacles and blockages in physical environments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     odors
    -0.50
     viață
    -0.49
    Хьажоргаш
    -0.49
     odor
    -0.48
     plowed
    -0.48
    EDEFAULT
    -0.47
     Oceanic
    -0.47
     theaters
    -0.47
     neighborhoods
    -0.46
     busted
    -0.46
    POSITIVE LOGITS
     duly
    0.56
     remon
    0.48
     sello
    0.46
    日閲覧
    0.44
     spl
    0.43
     round
    0.42
     ligiloj
    0.41
     manoeuvre
    0.41
     legging
    0.41
     jud
    0.41
    Activations Density 0.285%

    No Known Activations