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. 12845
    Prev
    Next
    INDEX
    Explanations

    technical specifications and requirements related to processes and materials

    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
    DockStyle
    -0.58
     defStyleAttr
    -0.57
    imentel
    -0.56
     Aurelius
    -0.55
    킨
    -0.55
    اریخ
    -0.51
    ⋙
    -0.49
    новниш
    -0.49
    RenderAtEndOf
    -0.48
     potuto
    -0.48
    POSITIVE LOGITS
     preferably
    0.86
    preferably
    0.82
     Preferably
    0.76
    才行
    0.75
     atleast
    0.69
     ideally
    0.68
    要有
    0.68
    DataAnnotations
    0.64
    rably
    0.61
     Ideally
    0.60
    Activations Density 0.689%

    No Known Activations