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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 9858
    Prev
    Next
    INDEX
    Explanations

    technical terms related to diabetes management and medication delivery systems

    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
     '\\;'
    -0.83
     فريبيس
    -0.80
     imageNamed
    -0.80
    ]")]
    -0.76
     Exactos
    -0.74
    хьтан
    -0.73
    ViewFeatures
    -0.73
    oredCriteria
    -0.73
     CanadaChoose
    -0.71
    principalColumn
    -0.71
    POSITIVE LOGITS
    gerät
    0.71
     compressor
    0.65
     calculator
    0.65
     equipment
    0.62
     aparat
    0.61
     apparatus
    0.61
     spectrometer
    0.61
     oven
    0.59
     Gerät
    0.59
     stove
    0.58
    Activations Density 0.668%

    No Known Activations