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. 2-GEMMASCOPE-RES-16K
    6. 2214
    Prev
    Next
    INDEX
    Explanations

    curly braces and their usage in code structures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.62
     Superhost
    -0.61
     '\\;'
    -0.57
    contentLoaded
    -0.56
     للاسماء
    -0.56
     يتيمه
    -0.55
    LookAnd
    -0.53
     transfieras
    -0.52
    Diweddarwch
    -0.52
    delwed
    -0.51
    POSITIVE LOGITS
    TagMode
    0.63
    CGRectMake
    0.62
    ']],
    0.62
    ={{
    0.61
    Kalb
    0.60
     BoxDecoration
    0.57
    >//
    0.56
    eux
    0.54
    ConfigureAwait
    0.54
    >({
    0.53
    Activations Density 0.298%

    No Known Activations