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. 14-GEMMASCOPE-RES-16K
    6. 3107
    Prev
    Next
    INDEX
    Explanations

    elements and functions related to web page manipulation, specifically those involving JavaScript and selectors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 14-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_14/width_16k/average_l0_84
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.14.hook_resid_post
    Hook Layer
    14
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Rohy
    -0.71
    SharedCtor
    -0.66
    BeginInit
    -0.63
     AssemblyCulture
    -0.63
    IsMutable
    -0.62
    Personendaten
    -0.61
    PropertyChanging
    -0.59
     concentra
    -0.57
     defaultstate
    -0.56
     متعلقه
    -0.56
    POSITIVE LOGITS
     Majefty
    0.62
    UrlResolution
    0.62
     Efq
    0.57
    ...')
    0.57
     Chrift
    0.56
    pośred
    0.54
     Chrif
    0.54
     Chriſt
    0.54
     ftate
    0.53
     XNUMX
    0.53
    Activations Density 0.103%

    No Known Activations