© 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. 22-GEMMASCOPE-RES-16K
    6. 6473
    Prev
    Next
    INDEX
    Explanations

    references to digital technology and products

    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
    spreis
    -0.40
    cuerdo
    -0.40
     stmt
    -0.39
     ihti
    -0.39
     Reak
    -0.39
    taciones
    -0.38
     wą
    -0.38
     wzor
    -0.38
     Attempt
    -0.37
     Example
    -0.37
    POSITIVE LOGITS
     digital
    1.01
    Digital
    0.96
    DIGITAL
    0.93
     DIGITAL
    0.93
    digital
    0.90
     Digital
    0.89
     digitally
    0.81
     digitale
    0.77
     digitalen
    0.74
     electronic
    0.72
    Activations Density 0.252%

    No Known Activations