© 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. 7085
    Prev
    Next
    INDEX
    Explanations

    terms related to medicine, healthcare, and nutritional elements

    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
     and
    -0.47
    however
    -0.46
     however
    -0.45
    rawtypes
    -0.44
    magnitude
    -0.44
    
    -0.44
    ➟
    -0.43
     guards
    -0.42
     ivelany
    -0.42
     jednak
    -0.41
    POSITIVE LOGITS
    GIVEREF
    0.48
    magitan
    0.40
    createTextNode
    0.37
    ChrTalk
    0.36
     ujarnya
    0.36
     تانيه
    0.35
     pouvoit
    0.35
    SequentialGroup
    0.35
     calificación
    0.35
     INTERESAR
    0.34
    Activations Density 1.269%

    No Known Activations