© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 35-GEMMASCOPE-RES-16K
    11. 14162
    Prev
    Next
    INDEX
    Explanations

    the verb "to be" in various forms and negations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/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.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    erker
    -0.54
     $_(
    -0.49
    __*/
    -0.48
    riwal
    -0.47
    amoan
    -0.47
    principalTable
    -0.45
    []>(
    -0.45
    الحياه
    -0.45
    Predecesor
    -0.44
     volontà
    -0.43
    POSITIVE LOGITS
     necessarily
    0.59
    necessarily
    0.56
     anymore
    0.54
     anybody
    0.53
    <bos>
    0.48
     exactly
    0.48
     anything
    0.47
     anywhere
    0.46
    ’
    0.46
     anyone
    0.44
    Activations Density 0.132%

    No Known Activations