© 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. 33-GEMMASCOPE-RES-16K
    11. 7960
    Prev
    Next
    INDEX
    Explanations

    references to clarity and clear communication

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     незавершена
    -0.50
    pherals
    -0.44
    gapa
    -0.43
    })()
    -0.42
    ItemLayout
    -0.41
    CELLANEOUS
    -0.40
    liothè
    -0.40
    EFAULT
    -0.38
     ContentValues
    -0.38
    Numerade
    -0.37
    POSITIVE LOGITS
     clear
    2.70
    clear
    2.36
     CLEAR
    2.27
     clarity
    2.25
     Clear
    2.25
     clearer
    2.22
     clearest
    2.17
    Clear
    2.16
     clearly
    2.13
    CLEAR
    1.98
    Activations Density 0.954%

    No Known Activations