Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 11040
    Prev
    Next
    INDEX
    Explanations

    references to wars, battles, and conflicts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    دانشنامهٔ
    -0.69
     NSCoder
    -0.61
    GOTREF
    -0.57
    timewa
    -0.56
     reca
    -0.56
    antMatchers
    -0.55
    respec
    -0.55
    Sucesor
    -0.55
     ويكيپيديا
    -0.53
    VertexAttrib
    -0.53
    POSITIVE LOGITS
     battle
    1.69
     battles
    1.64
     fight
    1.62
    fight
    1.61
     fights
    1.50
     fought
    1.49
     Fight
    1.40
    fights
    1.36
     battled
    1.34
     fighting
    1.34
    Activations Density 0.258%

    No Known Activations