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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 37-GEMMASCOPE-RES-16K
    11. 4791
    Prev
    Next
    INDEX
    Explanations

    references to building floors and spatial relationships within structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 37-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_37/width_16k/average_l0_124
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.37.hook_resid_post
    Hook Layer
    37
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Datuak
    -0.40
     cadeia
    -0.36
    */].
    -0.36
    пыт
    -0.32
     achtergrond
    -0.32
    átula
    -0.32
    jimo
    -0.31
     فہرست
    -0.31
     sahip
    -0.31
    ValueStyle
    -0.30
    POSITIVE LOGITS
     floor
    3.03
     floors
    2.67
     Floor
    2.66
    floor
    2.58
    Floor
    2.53
     FLOOR
    2.45
    floors
    2.28
     Floors
    2.23
    FLOOR
    2.17
     lantai
    1.91
    Activations Density 0.260%

    No Known Activations