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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 8147
    Prev
    Next
    INDEX
    Explanations

    references to data structures and programming constructs related to HashMap and similar collections

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -0.84
     Lordships
    -0.77
    EndGlobalSection
    -0.73
    Hentet
    -0.73
    tanleria
    -0.71
    setupUi
    -0.71
    webElementXpaths
    -0.70
     BrowserModule
    -0.69
     <<<<<<<<<<<<<<
    -0.69
    complexContent
    -0.63
    POSITIVE LOGITS
    gle
    0.59
    HashMap
    0.55
    ]();
    0.53
    衍
    0.52
     HashMap
    0.51
     ecological
    0.51
    べて
    0.50
     loạt
    0.50
    长
    0.50
    ски
    0.49
    Activations Density 2.923%

    No Known Activations