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. 24-GEMMASCOPE-RES-16K
    6. 13914
    Prev
    Next
    INDEX
    Explanations

    instances of potential risks and repairs related to machinery or vehicles

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

    Corrosion, shorts, and defects

    np_acts-logits-general · gemini-2.0-flash

    faults, leaks, and damage

    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
    msgTypes
    -0.53
    AlterField
    -0.53
    تقاوى
    -0.50
    uticos
    -0.50
    godic
    -0.50
    tamount
    -0.50
     yyr
    -0.49
    ESSION
    -0.48
    λευτα
    -0.47
    bezier
    -0.46
    POSITIVE LOGITS
     broken
    1.11
     leaky
    0.92
     missing
    0.92
     leaks
    0.91
    broken
    0.89
     spills
    0.88
     faulty
    0.86
     theft
    0.86
     spilled
    0.85
     stolen
    0.83
    Activations Density 0.351%

    No Known Activations