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 - 65k
    5. 12-GEMMASCOPE-RES-65K
    6. 43358
    Prev
    Next
    INDEX
    Explanations

    specific terms and phrases related to data handling or technical specifications

    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-65k
    Configuration
    google/gemma-scope-2b-pt-res/layer_12/width_65k/average_l0_72
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    65,536
    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
     estekak
    -1.01
    expandindo
    -0.93
    Personendaten
    -0.92
    دانشنامهٔ
    -0.88
     tartalomajánló
    -0.85
     autorytatywna
    -0.81
    脚注の使い方
    -0.81
     متعلقه
    -0.80
    torie
    -0.79
    ########.
    -0.79
    POSITIVE LOGITS
     stř
    0.63
     linho
    0.62
     tæ
    0.56
     sää
    0.55
     cuchillo
    0.54
    ュ
    0.54
     Sha
    0.53
     Ins
    0.53
     Ste
    0.53
     penghar
    0.52
    Activations Density 0.392%

    No Known Activations