© 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. 3656
    Prev
    Next
    INDEX
    Explanations

    instances of the word "located" and its variations, indicating a focus on geographical or spatial information

    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
     visibility
    -0.47
    ArgsConstructor
    -0.47
     bearings
    -0.43
     înc
    -0.41
     dreams
    -0.41
     instinct
    -0.40
    inversion
    -0.40
     sarili
    -0.39
    Yield
    -0.39
     håll
    -0.39
    POSITIVE LOGITS
     accessed
    1.21
     contacted
    1.20
     contacting
    1.05
    accessed
    0.96
     located
    0.93
     accessing
    0.90
     Accessed
    0.84
    Accessed
    0.78
     Located
    0.75
     locate
    0.73
    Activations Density 0.094%

    No Known Activations