© 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. 11046
    Prev
    Next
    INDEX
    Explanations

    punctuation and transitional phrases in the text

    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
     although
    -0.57
     despite
    -0.57
     THOUGH
    -0.52
     spite
    -0.51
     eftersom
    -0.47
    aunque
    -0.47
     there
    -0.46
     it
    -0.46
     nonostante
    -0.46
     meskipun
    -0.45
    POSITIVE LOGITS
    ScopeManager
    0.57
     conversely
    0.51
     Likewise
    0.51
    RTLR
    0.51
     Similarly
    0.50
    Similarly
    0.49
     Conversely
    0.49
    Likewise
    0.49
     contrario
    0.48
     '\\;'
    0.47
    Activations Density 0.780%

    No Known Activations