© 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. 36-GEMMASCOPE-RES-16K
    11. 16320
    Prev
    Next
    INDEX
    Explanations

    superlative forms and references to significant achievements or qualities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/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.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    +#+#
    -0.68
    CloseOperation
    -0.58
    Personendaten
    -0.56
    ContentLoaded
    -0.48
    IsMutable
    -0.47
     Enough
    -0.47
     insuffisamment
    -0.45
    ">—
    -0.44
    脚注の使い方
    -0.44
    WireFormatLite
    -0.44
    POSITIVE LOGITS
     ever
    1.52
     imaginable
    1.37
     EVER
    1.21
    ever
    1.11
     ooit
    1.04
     possible
    0.99
     jemals
    0.98
     überhaupt
    0.96
     conceivable
    0.95
    EVER
    0.94
    Activations Density 0.304%

    No Known Activations