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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 15-GEMMASCOPE-RES-16K
    6. 3977
    Prev
    Next
    INDEX
    Explanations

    terms related to viruses and their persistent nature, particularly in the context of technology or systems

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    webElement
    -0.54
    reszcie
    -0.51
    Loading
    -0.49
    })();
    
    -0.46
    subpackage
    -0.42
    WriteAttribute
    -0.41
    よいよ
    -0.40
    sira
    -0.40
    alou
    -0.40
    hdashline
    -0.39
    POSITIVE LOGITS
     respawn
    0.98
     rebound
    0.96
     regenerated
    0.83
     rebounds
    0.83
     Wieder
    0.81
     restarts
    0.81
     reinstatement
    0.80
     Regener
    0.80
     comeback
    0.79
     resets
    0.79
    Activations Density 0.246%

    No Known Activations