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. 3-GEMMASCOPE-RES-16K
    6. 10932
    Prev
    Next
    INDEX
    Explanations

    occurrences of the substring "ng"

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    SequentialGroup
    -0.78
    #+#
    -0.76
    BeginInit
    -0.74
    ValueStyle
    -0.70
    LLocation
    -0.70
    createClass
    -0.67
    esgue
    -0.67
    InstanceState
    -0.66
     Pong
    -0.64
    KEYCODE
    -0.63
    POSITIVE LOGITS
     ng
    1.06
     om
    0.97
     NG
    0.87
     transformation
    0.83
     transformations
    0.79
    ='$
    0.78
     Om
    0.77
    Om
    0.74
    transformation
    0.73
     Theron
    0.72
    Activations Density 0.105%

    No Known Activations