© 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. 22-GEMMASCOPE-RES-16K
    11. 6546
    Prev
    Next
    INDEX
    Explanations

    terms related to characters and their attributes in a game context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ſche
    -0.68
     myſelf
    -0.66
     ſch
    -0.61
     ſte
    -0.61
     ſol
    -0.59
     juſt
    -0.59
     Anſ
    -0.59
     cauſe
    -0.59
     pleaſure
    -0.58
     fubject
    -0.58
    POSITIVE LOGITS
     mempertahankan
    0.47
     unaffected
    0.43
     yanı
    0.43
     unchanged
    0.40
     utrzy
    0.39
     untouched
    0.39
     aside
    0.38
     obviously
    0.38
     zů
    0.38
     atrav
    0.38
    Activations Density 0.931%

    No Known Activations