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. 53366
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "anywhere."

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

    location markers

    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
    исленность
    -0.80
    gatsby
    -0.68
    n
    -0.67
    a
    -0.67
    s
    -0.65
    ApiModelProperty
    -0.64
    io
    -0.60
    initComponents
    -0.59
    toThrow
    -0.59
    tanooga
    -0.58
    POSITIVE LOGITS
    存于互联网档案馆
    0.92
     poffible
    0.91
     myſelf
    0.90
     Everywhere
    0.88
     becauſe
    0.88
     Monfieur
    0.85
     Nowhere
    0.85
     everywhere
    0.82
     themſelves
    0.81
    Anywhere
    0.81
    Activations Density 0.013%

    No Known Activations