© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 1223
    Prev
    Next
    INDEX
    Explanations

    dates and specific time markers

    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
     '\\;'
    -0.49
    OnClickListener
    -0.47
    енча
    -0.39
     Frenchman
    -0.36
    chappement
    -0.35
    Keyboard
    -0.35
    三人
    -0.35
     Krieg
    -0.35
    oiseau
    -0.34
    ichier
    -0.34
    POSITIVE LOGITS
    Nov
    0.86
     Nov
    0.82
     flex
    0.76
    Oct
    0.75
     Oct
    0.73
    llbracket
    0.68
     Sept
    0.68
     nov
    0.66
     Flex
    0.66
    Sept
    0.65
    Activations Density 0.083%

    No Known Activations