© 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. 37-GEMMASCOPE-RES-16K
    11. 4301
    Prev
    Next
    INDEX
    Explanations

    prepositions indicating relationships and connections within sentences

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ########.
    -0.63
    twimg
    -0.60
    yntaxException
    -0.58
    tonode
    -0.57
    rawDesc
    -0.55
    lapsingToolbar
    -0.55
     betweenstory
    -0.53
    WriteBarrier
    -0.52
     ujednoznacz
    -0.51
    новниш
    -0.50
    POSITIVE LOGITS
     arguably
    0.47
     regulation
    0.45
     emphatic
    0.44
     perhaps
    0.44
     consecutive
    0.43
     impressive
    0.43
     quizá
    0.42
     limited
    0.41
     what
    0.40
     crunch
    0.40
    Activations Density 0.162%

    No Known Activations