© 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. 0-GEMMASCOPE-RES-16K
    11. 8938
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating excitement or emotional engagement, as well as terms related to amendments and revisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    omotor
    -0.54
     erythro
    -0.52
     station
    -0.52
     cerv
    -0.51
     reper
    -0.50
     cord
    -0.50
     quint
    -0.50
    ExecutionContext
    -0.50
     $_(
    -0.50
     ultras
    -0.50
    POSITIVE LOGITS
    ########.
    0.77
    Appro
    0.73
    appro
    0.69
     pendekatan
    0.61
     approximation
    0.58
     aproxima
    0.57
     Übernach
    0.57
     abordagem
    0.57
     approximations
    0.57
     Wikiseite
    0.57
    Activations Density 0.277%

    No Known Activations