© 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. 40-GEMMASCOPE-RES-16K
    11. 5607
    Prev
    Next
    INDEX
    Explanations

    technical terms and conditions related to software or programming

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 40-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_40/width_16k/average_l0_125
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.40.hook_resid_post
    Hook Layer
    40
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Pilot
    -0.92
    Passage
    -0.90
    Paper
    -0.90
    Plate
    -0.89
    Plot
    -0.89
    Press
    -0.88
    Post
    -0.88
    Pass
    -0.88
    Pressure
    -0.87
    Panel
    -0.86
    POSITIVE LOGITS
     הפ
    0.47
     p
    0.43
     პ
    0.41
    ゚
    0.39
    Diweddarwch
    0.39
    Geplaatst
    0.38
     պ
    0.34
     р
    0.32
    piecze
    0.32
     pr
    0.30
    Activations Density 4.016%

    No Known Activations