© 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. 0-GEMMASCOPE-RES-16K
    6. 2488
    Prev
    Next
    INDEX
    Explanations

    references to terminal structures or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pouvoit
    -0.71
     Económica
    -0.71
     infierno
    -0.70
     kasarigan
    -0.70
     queſta
    -0.68
    +#+#
    -0.67
     Eſ
    -0.66
     pleaſure
    -0.66
     väli
    -0.65
     feroit
    -0.63
    POSITIVE LOGITS
     terminal
    0.65
     Terminal
    0.56
     Li
    0.56
     article
    0.43
     manifest
    0.41
     li
    0.40
     trace
    0.39
     stream
    0.39
     c
    0.38
     pic
    0.38
    Activations Density 0.242%

    No Known Activations