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. 1436
    Prev
    Next
    INDEX
    Explanations

    HTML markup and structure elements

    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
    kháu
    -0.93
    Hozzáférés
    -0.88
    errHandler
    -0.88
    StructEnd
    -0.88
    Personendaten
    -0.87
    Rhestr
    -0.86
    Šaltiniai
    -0.86
    HostException
    -0.85
    rawDesc
    -0.84
    LLocation
    -0.82
    POSITIVE LOGITS
    続いて
    0.43
    ↵
    0.42
     vägen
    0.41
     elämä
    0.41
     accanto
    0.38
     Ocak
    0.37
     Petron
    0.37
    id
    0.37
     skippy
    0.36
    Category
    0.36
    Activations Density 0.167%

    No Known Activations