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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 14011
    Prev
    Next
    INDEX
    Explanations

    technical terms and identifiers related to programming or data structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_22/width_16k/average_l0_123
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    localctx
    -0.47
    princip
    -0.47
    er
    -0.45
     martyrs
    -0.44
    dafx
    -0.44
    Đi
    -0.44
    Kong
    -0.44
    marker
    -0.43
     Infórmanos
    -0.43
    chân
    -0.43
    POSITIVE LOGITS
    vv
    0.86
    vav
    0.79
    VIAF
    0.79
    v
    0.79
    iv
    0.70
    V
    0.69
    vă
    0.69
    vula
    0.68
    vy
    0.66
    VV
    0.65
    Activations Density 1.038%

    No Known Activations