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. 15-GEMMASCOPE-RES-16K
    6. 2268
    Prev
    Next
    INDEX
    Explanations

    phrases and expressions related to technology and its impact on daily life

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    arbeitung
    -0.48
     dẫn
    -0.46
    nok
    -0.45
    [++
    -0.45
     bast
    -0.43
     her
    -0.42
    ihr
    -0.42
     Cont
    -0.42
    oure
    -0.41
    bast
    -0.41
    POSITIVE LOGITS
     takto
    0.96
    脚注の使い方
    0.95
     چنین
    0.94
     sådan
    0.90
     such
    0.86
     demikian
    0.85
    Such
    0.85
    such
    0.83
     böyle
    0.83
     ilyen
    0.80
    Activations Density 0.276%

    No Known Activations