© 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. 2-GEMMASCOPE-RES-16K
    11. 8744
    Prev
    Next
    INDEX
    Explanations

    references to academic and author names in citations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    httphttps
    -1.03
     queſta
    -1.02
    majánló
    -1.00
    хьтан
    -0.92
     noDo
    -0.92
     ſche
    -0.89
     autorytatywna
    -0.89
     ſch
    -0.87
     Italijanski
    -0.87
     Мексичка
    -0.86
    POSITIVE LOGITS
     P
    0.42
     L
    0.40
     S
    0.40
     W
    0.39
     R
    0.39
     C
    0.38
     B
    0.38
     F
    0.37
     E
    0.37
     M
    0.37
    Activations Density 0.386%

    No Known Activations