© 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. 9-GEMMASCOPE-RES-16K
    11. 9209
    Prev
    Next
    INDEX
    Explanations

    relationships that indicate connections or comparisons

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_9/width_16k/average_l0_100
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    撮り
    -0.39
     otomatig
    -0.39
    localPosition
    -0.36
     sắc
    -0.34
    Grüße
    -0.34
    fromCharCode
    -0.34
    autoconfigure
    -0.33
     affordability
    -0.33
    Referencer
    -0.32
     puntas
    -0.32
    POSITIVE LOGITS
    AddTagHelper
    0.68
     anſ
    0.66
     whoſe
    0.63
     chofe
    0.63
     againſt
    0.60
    bindValue
    0.56
     cauſe
    0.56
     purpoſe
    0.56
     ſtre
    0.56
     raiſ
    0.55
    Activations Density 0.471%

    No Known Activations