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. 12-GEMMASCOPE-RES-16K
    6. 12038
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to chemical reactions and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_16k/average_l0_82
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Cur
    -0.52
     ach
    -0.48
     Cur
    -0.48
    CUR
    -0.46
     cur
    -0.43
    ówek
    -0.43
    报记者
    -0.43
    ми
    -0.42
    Ach
    -0.42
    sweise
    -0.42
    POSITIVE LOGITS
    enumii
    0.89
    enumi
    0.89
    RetentionPolicy
    0.70
    abetes
    0.69
     ddelweddau
    0.69
    PropertyGroup
    0.65
    terase
    0.65
    Obrázky
    0.65
     समीक्षक
    0.64
     становника
    0.64
    Activations Density 1.099%

    No Known Activations