© 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. 24-GEMMASCOPE-RES-16K
    6. 16141
    Prev
    Next
    INDEX
    Explanations

    references to digital computers and their historical development

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    computers or computing

    np_acts-logits-general · gemini-2.0-flash

    computer hardware or types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    IsMutable
    -0.82
     nahilalakip
    -0.69
     שוליים
    -0.68
    ttemberg
    -0.63
    +#+#
    -0.61
     autorytatywna
    -0.61
    jsonwebtoken
    -0.61
    RTDA
    -0.58
    __':
    
    -0.58
     WebGL
    -0.57
    POSITIVE LOGITS
     computer
    1.03
    computer
    0.88
     Computer
    0.86
     computers
    0.85
    Computer
    0.81
     komputer
    0.77
     punched
    0.76
     COMPUTER
    0.72
     computing
    0.72
     compter
    0.71
    Activations Density 0.657%

    No Known Activations