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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 7996
    Prev
    Next
    INDEX
    Explanations

    references to sports awards and collegiate championships

    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
    makeText
    -0.46
     national
    -0.39
    NATIONAL
    -0.37
     National
    -0.37
    National
    -0.36
     Национальный
    -0.35
     nacional
    -0.33
    national
    -0.33
     NATIONAL
    -0.33
    scroll
    -0.31
    POSITIVE LOGITS
    Tikang
    0.75
    DockStyle
    0.68
    StructEnd
    0.66
    astéroïdes
    0.62
    ]")]
    0.61
     standings
    0.61
     commissioner
    0.60
    testens
    0.60
    [@BOS@]
    0.59
     Playoffs
    0.59
    Activations Density 0.222%

    No Known Activations