© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 33-GEMMASCOPE-RES-16K
    6. 728
    Prev
    Next
    INDEX
    Explanations

    sentences that end with punctuation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     shes
    -0.58
    Witam
    -0.55
     gladiator
    -0.52
    uttgart
    -0.52
     arent
    -0.51
     linebacker
    -0.51
     mermaid
    -0.50
     badminton
    -0.50
     multiplayer
    -0.50
     werewolf
    -0.50
    POSITIVE LOGITS
     The
    1.11
     There
    0.98
     It
    0.93
     This
    0.92
     Some
    0.86
     They
    0.84
     For
    0.82
     In
    0.82
     When
    0.80
     That
    0.80
    Activations Density 2.551%

    No Known Activations