© 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. 35-GEMMASCOPE-RES-16K
    11. 7033
    Prev
    Next
    INDEX
    Explanations

    concepts related to space and organization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 35-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_35/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.35.hook_resid_post
    Hook Layer
    35
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ))]
    -0.27
    APORE
    -0.26
    zewod
    -0.24
    رفته
    -0.24
     متعلقه
    -0.24
    )};
    -0.23
    })`
    -0.23
    >({
    -0.23
    AutoScaleMode
    -0.23
    ::__
    -0.23
    POSITIVE LOGITS
     space
    1.96
     ruimte
    1.71
     espacio
    1.64
    space
    1.61
     espaço
    1.59
     spazio
    1.52
     SPACE
    1.50
    Space
    1.47
     room
    1.45
    スペース
    1.45
    Activations Density 0.443%

    No Known Activations