© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 14985
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly parentheses and their closing counterparts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     hjælp
    -0.58
     hjelp
    -0.57
    rink
    -0.52
     klachten
    -0.50
    inburgh
    -0.49
     obuv
    -0.49
     bardak
    -0.48
     spørgsmål
    -0.48
    IFIER
    -0.47
    ptid
    -0.47
    POSITIVE LOGITS
    )")
    1.07
    )')
    1.01
    )</
    0.98
    ?)
    0.97
    )])
    0.95
     {})
    0.93
    )-
    0.90
    ).)
    0.90
    )]
    0.88
    ?),
    0.88
    Activations Density 0.652%

    No Known Activations