© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 9-GEMMASCOPE-RES-16K
    6. 14935
    Prev
    Next
    INDEX
    Explanations

    method declaration and function test keyword patterns in code

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 9-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_9/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.9.hook_resid_post
    Hook Layer
    9
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    CloseOperation
    -1.10
     autorytatywna
    -0.93
    httphttps
    -0.87
    IndentedString
    -0.82
    ColumnHeaders
    -0.77
    EndInit
    -0.74
    цездатний
    -0.72
    Autoritní
    -0.70
    RTLI
    -0.70
    +#+#
    -0.70
    POSITIVE LOGITS
     stessa
    0.58
     stesso
    0.51
    دل
    0.48
    曖昧さ回避
    0.41
     mesma
    0.41
     mismos
    0.41
    mauer
    0.40
    czaj
    0.40
    방
    0.40
    engelsk
    0.40
    Activations Density 1.049%

    No Known Activations