© 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. 0-GEMMASCOPE-RES-16K
    11. 7149
    Prev
    Next
    INDEX
    Explanations

    phrases indicating usefulness or benefit in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Vidite
    -0.98
     Савезне
    -0.76
    +#+
    -0.75
    GEBURTSDATUM
    -0.71
     mxArray
    -0.69
     betweenstory
    -0.68
    IndentedString
    -0.68
     preg
    -0.67
     Biôgrafia
    -0.66
    RTLR
    -0.64
    POSITIVE LOGITS
     useful
    1.68
     Useful
    1.47
    Useful
    1.45
     helpful
    1.41
     beneficial
    1.34
     útiles
    1.30
    useful
    1.28
     útil
    1.20
     полез
    1.20
     Helpful
    1.16
    Activations Density 0.198%

    No Known Activations