© 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. 33-GEMMASCOPE-RES-16K
    11. 7567
    Prev
    Next
    INDEX
    Explanations

    conjunctions and transition phrases that indicate contrast or additional information

    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
    IndentedString
    -0.73
    prepareStatement
    -0.70
    oredCriteria
    -0.66
     gynhyrchwyd
    -0.61
    InitVars
    -0.61
     OFDb
    -0.58
    IBOutlet
    -0.57
     виправивши
    -0.57
     EdgeInsets
    -0.57
    AddHtmlAttribute
    -0.57
    POSITIVE LOGITS
     although
    1.37
     while
    1.27
     despite
    1.15
     meskipun
    1.10
     since
    1.09
     when
    1.08
     obwohl
    1.05
    although
    1.05
     during
    1.03
    while
    1.00
    Activations Density 1.808%

    No Known Activations