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. 11210
    Prev
    Next
    INDEX
    Explanations

    code structures or elements related to lists and events in programming

    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
    Portale
    -0.64
     disant
    -0.61
    logenetic
    -0.61
    querque
    -0.58
     fevere
    -0.58
    berdayakan
    -0.58
    Portail
    -0.57
     pleaſure
    -0.57
    nước
    -0.56
    SerializedSize
    -0.55
    POSITIVE LOGITS
     []:
    2.06
    ValueStyle
    1.20
     estimés
    1.02
    DebuggerNonUser
    1.01
     "..\..\..\
    0.95
    )))),
    0.81
     "..\..\
    0.77
    stdio
    0.76
    WebVitals
    0.75
     actionPerformed
    0.71
    Activations Density 0.006%

    No Known Activations