© 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-2-2B
    4. Residual Stream - 16k
    5. 23-GEMMASCOPE-RES-16K
    6. 8663
    Prev
    Next
    INDEX
    Explanations

    structured data types and their properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Adopted
    -0.61
    WriteTagHelper
    -0.60
     adopted
    -0.53
     Marlon
    -0.50
     Millar
    -0.47
     adoption
    -0.47
     adopt
    -0.46
    Adopted
    -0.46
     sierp
    -0.45
    Ade
    -0.45
    POSITIVE LOGITS
                
    1.31
     ninth
    0.77
     nine
    0.77
     ninety
    0.69
    ninth
    0.69
     المعيارى
    0.69
    PRNewswire
    0.68
     Ninth
    0.67
    ⁹
    0.66
     propOrder
    0.64
    Activations Density 0.123%

    No Known Activations