© 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. 20-GEMMASCOPE-RES-16K
    11. 570
    Prev
    Next
    INDEX
    Explanations

    references to specific items or entities being discussed

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    the word "These" at the start of sentences or clauses.

    oai_token-act-pair · claude-3-5-haiku-20241022Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     vœux
    -0.59
     épaules
    -0.54
    Abend
    -0.52
     preuves
    -0.52
     a
    -0.51
     tiroirs
    -0.51
     Schilling
    -0.50
    的一个
    -0.49
     inconvénients
    -0.49
    instancetype
    -0.49
    POSITIVE LOGITS
     these
    0.88
     those
    0.75
     egne
    0.68
    these
    0.67
     THESE
    0.67
    These
    0.66
     theses
    0.66
     These
    0.64
    those
    0.63
     fleste
    0.63
    Activations Density 0.151%

    No Known Activations