© 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-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5798
    Prev
    Next
    INDEX
    Explanations

    references to the Fifth Amendment and related legal concepts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ricette
    -0.54
    Демографія
    -0.52
     NSCoder
    -0.51
     ROUT
    -0.50
     copertura
    -0.50
    RenderAtEndOf
    -0.49
    rature
    -0.49
    URLConnection
    -0.49
    onAttach
    -0.49
     McClure
    -0.48
    POSITIVE LOGITS
    5
    1.34
     Five
    1.00
     five
    0.97
    five
    0.94
    Five
    0.92
     cinco
    0.91
     Fifth
    0.91
    5
    0.88
     fifth
    0.87
     cinq
    0.85
    Activations Density 0.732%

    No Known Activations