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-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 9343
    Prev
    Next
    INDEX
    Explanations

    phrases indicating causation or relationships between events

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     '{@
    -0.80
    Demografía
    -0.68
     strå
    -0.67
     escuchadas
    -0.67
     batalha
    -0.67
     fluence
    -0.66
    Демографія
    -0.66
     apparti
    -0.65
    basicConfig
    -0.64
    BagLayout
    -0.64
    POSITIVE LOGITS
     eventual
    0.84
     causes
    0.79
     caused
    0.78
     resulted
    0.78
    导致
    0.78
     resulting
    0.77
     increased
    0.77
     causing
    0.74
     a
    0.72
     terjadinya
    0.72
    Activations Density 0.345%

    No Known Activations