© 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. 39-GEMMASCOPE-RES-16K
    11. 3394
    Prev
    Next
    INDEX
    Explanations

    contractions, particularly those expressing possession or negation

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 39-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_39/width_16k/average_l0_131
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.39.hook_resid_post
    Hook Layer
    39
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Administrativna
    -1.18
     незавершена
    -1.11
    AndEndTag
    -1.08
     للمعارف
    -1.05
    RenderAtEndOf
    -1.02
    ReusableCell
    -1.00
    TypedDataSet
    -0.99
     '\\;'
    -0.98
    tagHelperRunner
    -0.97
    StoryboardSegue
    -0.97
    POSITIVE LOGITS
    ll
    0.27
    d
    0.21
    ve
    0.19
    does
    0.16
     perhaps
    0.15
     really
    0.15
    would
    0.15
    really
    0.15
    so
    0.14
     wouldn
    0.14
    Activations Density 0.083%

    No Known Activations