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. 16-GEMMASCOPE-RES-16K
    6. 6449
    Prev
    Next
    INDEX
    Explanations

    references to children's artwork and their recognition in exhibitions

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

    Numbers followed by specific units or descriptions

    np_acts-logits-general · gemini-2.0-flash

    numbers multiplied by thousand

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/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.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.87
     BoxDecoration
    -0.76
     ddelweddau
    -0.72
     []:
    -0.69
     itſelf
    -0.63
     Conſ
    -0.63
    RSpec
    -0.63
     Anſ
    -0.62
     Houſe
    -0.61
     Jefus
    -0.61
    POSITIVE LOGITS
    featureID
    0.62
    AndEndTag
    0.54
     mutate
    0.53
    +:+
    0.52
    lastIndex
    0.52
    ineno
    0.49
     Organisations
    0.47
    msgTypes
    0.46
    rrggbb
    0.46
    mators
    0.46
    Activations Density 0.158%

    No Known Activations