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. 1-GEMMASCOPE-RES-16K
    6. 15069
    Prev
    Next
    INDEX
    Explanations

    references to the act of searching or discovering something

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    InitVars
    -0.78
    viewDidLoad
    -0.74
    tvguidetime
    -0.74
     autorytatywna
    -0.69
    发表于
    -0.67
     незавершена
    -0.66
    ftagPool
    -0.65
    Controllo
    -0.65
    Населення
    -0.64
    MeasureSpec
    -0.64
    POSITIVE LOGITS
     finding
    1.92
    finding
    1.82
     Find
    1.73
     find
    1.72
     Finding
    1.71
    Finding
    1.71
    Find
    1.62
     FIND
    1.60
    FIND
    1.26
     finds
    1.21
    Activations Density 0.144%

    No Known Activations