© 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. 11602
    Prev
    Next
    INDEX
    Explanations

    references to open-source software and its implications

    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
     StringTokenizer
    -0.56
    Descripció
    -0.54
    IGraphics
    -0.52
    Wholesale
    -0.50
     minOccurs
    -0.50
     congen
    -0.49
    
    -0.49
    celotti
    -0.48
    synthesize
    -0.48
    TestingModule
    -0.48
    POSITIVE LOGITS
     GitHub
    0.61
     Github
    0.53
     Git
    0.51
     github
    0.50
    GitHub
    0.49
     Mast
    0.45
     git
    0.44
     Discord
    0.44
     conmigo
    0.42
     comigo
    0.42
    Activations Density 1.501%

    No Known Activations