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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 12348
    Prev
    Next
    INDEX
    Explanations

    references to the name "Allard."

    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
     demo
    -0.64
     DEMO
    -0.64
    flu
    -0.63
     flu
    -0.62
    eeeeeeee
    -0.62
     Flu
    -0.61
    brities
    -0.61
    Flu
    -0.60
     Helios
    -0.60
    Enllaços
    -0.60
    POSITIVE LOGITS
    ard
    2.74
    ARD
    2.47
    ards
    2.06
    rd
    1.74
    ARDS
    1.53
    arda
    1.52
    Ard
    1.48
    ardin
    1.43
    ardo
    1.42
    ardi
    1.39
    Activations Density 0.221%

    No Known Activations