© 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. 36-GEMMASCOPE-RES-16K
    11. 7844
    Prev
    Next
    INDEX
    Explanations

    references to the present time or specific instances, particularly focusing on the word "this."

    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
    ophageal
    -0.44
     unknownFields
    -0.41
    bootstrapcdn
    -0.41
    AccessorTable
    -0.40
     disambiguazione
    -0.39
    bcryptjs
    -0.38
     schafft
    -0.37
    plato
    -0.36
     unnoticed
    -0.36
     steder
    -0.36
    POSITIVE LOGITS
     regard
    1.01
     regards
    0.74
     particular
    0.68
    regard
    0.66
     particulières
    0.64
     instance
    0.63
     particulière
    0.62
     respecto
    0.56
    particular
    0.56
     Regard
    0.54
    Activations Density 0.252%

    No Known Activations