© 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. 1-GEMMASCOPE-RES-16K
    6. 8687
    Prev
    Next
    INDEX
    Explanations

    references to the web or web-related technologies

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '\\;'
    -0.56
    retudo
    -0.51
    Personensuche
    -0.50
     ello
    -0.44
    Apoll
    -0.40
    wack
    -0.40
    nalité
    -0.40
     edges
    -0.40
     Initialized
    -0.39
    omaly
    -0.39
    POSITIVE LOGITS
     Web
    1.45
    Web
    1.28
    web
    1.16
     web
    1.16
     WEB
    1.02
    WEB
    0.93
     website
    0.87
     webs
    0.85
     Website
    0.85
    webs
    0.84
    Activations Density 0.235%

    No Known Activations