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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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 - 65k
    5. 16-GEMMASCOPE-RES-65K
    6. 53373
    Prev
    Next
    INDEX
    Explanations

    words related to table structures or attributes, particularly in the context of data organization

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

    words ending in able or ible

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_65k/average_l0_128
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
    ing
    -0.85
    n
    -0.83
    es
    -0.72
    m
    -0.71
    N
    -0.60
    X
    -0.60
    2
    -0.59
    jspx
    -0.58
    en
    -0.57
    r
    -0.57
    POSITIVE LOGITS
     Efq
    1.06
    izable
    1.06
    ABLE
    1.05
    gable
    1.05
    chable
    1.03
    ourable
    1.02
     Theſe
    1.02
    vable
    1.02
    ^(@)
    1.02
     ་་
    1.01
    Activations Density 0.147%

    No Known Activations