© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 15-GEMMASCOPE-RES-16K
    11. 1832
    Prev
    Next
    INDEX
    Explanations

    the word "across" in various contexts, indicating a focus on the idea of spanning or connecting different areas or groups

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_15/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    cartItem
    -0.42
    ्य
    -0.42
    theless
    -0.42
    minValue
    -0.37
    Note
    -0.35
    年
    -0.34
    jMenuItem
    -0.34
    Ethylbenzene
    -0.34
     Synagogue
    -0.34
    ization
    -0.34
    POSITIVE LOGITS
     across
    1.40
     ACROSS
    1.38
    across
    1.37
     Across
    1.30
    Across
    1.26
     cross
    1.04
    cross
    1.01
     Cross
    0.93
     CROSS
    0.92
     crosses
    0.89
    Activations Density 0.067%

    No Known Activations