© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 7665
    Prev
    Next
    INDEX
    Explanations

    mentions and references to the season of fall

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    rungsseite
    -0.51
     kasarigan
    -0.47
     cuer
    -0.44
    (!__
    -0.44
     juventus
    -0.43
     Dile
    -0.42
     mỡ
    -0.42
    esModule
    -0.42
    webtoken
    -0.42
    пиона
    -0.42
    POSITIVE LOGITS
     falls
    3.47
     fall
    3.44
     falling
    3.38
     FALL
    3.06
    fall
    3.02
     Falling
    3.00
     fallen
    3.00
    falling
    2.97
     fell
    2.95
     Fall
    2.95
    Activations Density 0.126%

    No Known Activations