© 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. 5385
    Prev
    Next
    INDEX
    Explanations

    words and phrases associated with the establishment or creation of organizations, initiatives, and concepts

    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
    makeConstraints
    -0.79
    antMatchers
    -0.75
     חיצוניים
    -0.74
     Signalez
    -0.73
    FilterChain
    -0.69
    AnimationsModule
    -0.68
    TagHelper
    -0.67
     GetEnumerator
    -0.64
     onOptions
    -0.63
    IVEREF
    -0.63
    POSITIVE LOGITS
     thanks
    0.73
     specifically
    0.72
     expressly
    0.72
     because
    0.66
     partly
    0.66
     Reaktion
    0.66
     originally
    0.64
     специально
    0.63
     ursprünglich
    0.62
     purpose
    0.60
    Activations Density 0.347%

    No Known Activations