Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 11175
    Prev
    Next
    INDEX
    Explanations

    references to geographical locations and institutions related to sports

    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
     onBind
    -0.55
    TemporalType
    -0.53
     HttpNotFound
    -0.49
     ""],
    -0.48
    WEBPACK
    -0.47
    statechange
    -0.47
    awtextra
    -0.47
    ChromeDriver
    -0.46
     Préférences
    -0.45
     Савез
    -0.45
    POSITIVE LOGITS
     Palm
    0.67
    Palm
    0.66
    palm
    0.48
     palm
    0.43
     Broward
    0.38
     Coachella
    0.38
     Inlet
    0.38
    Boca
    0.38
     Boca
    0.38
     Raton
    0.37
    Activations Density 0.233%

    No Known Activations