© 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. 23-GEMMASCOPE-RES-16K
    11. 8910
    Prev
    Next
    INDEX
    Explanations

    information related to broadcasting and media outlets

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_23/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -0.59
    richTextPanel
    -0.54
     initComponents
    -0.54
    הערות
    -0.54
    клопе
    -0.53
    Garonne
    -0.52
     Мексичка
    -0.52
    География
    -0.51
    httphttps
    -0.51
     mergeFrom
    -0.51
    POSITIVE LOGITS
     agujas
    0.41
     Komunikasi
    0.40
     ää
    0.38
     zaś
    0.38
     instalaciones
    0.38
     rayas
    0.38
     hacerlo
    0.38
    ()?.
    0.36
     colonias
    0.35
     knji
    0.35
    Activations Density 0.810%

    No Known Activations