© 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. 8026
    Prev
    Next
    INDEX
    Explanations

    references to underlying factors or systems in a variety of contexts

    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
     Micha
    -0.42
    arakhand
    -0.42
    temporary
    -0.40
     fieltro
    -0.40
    hood
    -0.40
     temporary
    -0.40
     bricolaje
    -0.39
    cipline
    -0.39
     segno
    -0.39
     riconoscimento
    -0.39
    POSITIVE LOGITS
     leak
    0.71
     disk
    0.71
     leaked
    0.71
    Leak
    0.70
    OGND
    0.70
     leaks
    0.67
     leaking
    0.66
    Disk
    0.63
    leak
    0.63
    disk
    0.63
    Activations Density 0.165%

    No Known Activations