© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 8390
    Prev
    Next
    INDEX
    Explanations

    references to digital downloads and games

    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
    utilisons
    -0.93
     zwiſchen
    -0.87
     المعيارى
    -0.83
     Infórmanos
    -0.82
     zuſammen
    -0.81
    нгред
    -0.80
    tranno
    -0.77
     autorytatywna
    -0.76
     beſte
    -0.76
     ſei
    -0.75
    POSITIVE LOGITS
     |
    0.91
     -
    0.55
    |
    0.53
     ...
    0.49
     ·
    0.47
     …
    0.45
     by
    0.42
     –
    0.40
     ::
    0.38
     •
    0.37
    Activations Density 0.505%

    No Known Activations