© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 14950
    Prev
    Next
    INDEX
    Explanations

    specific geographical or organizational names and their relationships

    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
    ↵
    -0.27
     Mover
    -0.27
     acc
    -0.26
     Equ
    -0.26
     equ
    -0.25
    ↵↵↵
    -0.25
    اعد
    -0.25
    cences
    -0.25
     kaynağından
    -0.25
     Agree
    -0.25
    POSITIVE LOGITS
     resourceCulture
    0.80
    rungsseite
    0.69
     <<<<<<<<<<<<<<
    0.65
    thâu
    0.65
    afficheront
    0.65
     CanadaChoose
    0.65
     houſe
    0.65
     Biôgrafia
    0.64
    retudo
    0.63
    aarrggbb
    0.63
    Activations Density 2.359%

    No Known Activations