© 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. 27-GEMMASCOPE-RES-16K
    6. 9938
    Prev
    Next
    INDEX
    Explanations

    references to time periods and milestones

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Sala
    -0.34
    Jegyzetek
    -0.33
    www
    -0.32
     Ca
    -0.32
     Olivia
    -0.31
     Saito
    -0.31
     Bab
    -0.30
    处的
    -0.30
    Ca
    -0.29
     Cipri
    -0.29
    POSITIVE LOGITS
    AnchorStyles
    0.75
    AndroidJUnit
    0.73
    setVerticalGroup
    0.73
     виправивши
    0.68
     pinulongan
    0.65
     boyunca
    0.65
    ruptedException
    0.63
     ujednoznacz
    0.63
    ViewFeatures
    0.63
     itſelf
    0.63
    Activations Density 0.377%

    No Known Activations