© 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. 22-GEMMASCOPE-RES-16K
    11. 14689
    Prev
    Next
    INDEX
    Explanations

    the beginning of sentences or paragraphs in structured text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    asteroide
    -0.66
    AccessorTable
    -0.57
     estekak
    -0.55
    +#+#
    -0.55
    ="@+
    -0.54
    RRect
    -0.54
    الدراسه
    -0.53
     мәкал
    -0.50
    stateMutability
    -0.49
     Administrativna
    -0.48
    POSITIVE LOGITS
     Withdraw
    0.39
     徒歩
    0.38
    ÍSTICAS
    0.38
     EconPapers
    0.38
     Partly
    0.37
    ISCH
    0.37
     huur
    0.36
     genomen
    0.36
     withdrawn
    0.36
     campana
    0.34
    Activations Density 0.099%

    No Known Activations