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. 0-GEMMASCOPE-RES-16K
    6. 8026
    Prev
    Next
    INDEX
    Explanations

    the verb "are" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     is
    -1.07
     was
    -0.97
     
    -0.83
     has
    -0.76
    ↵↵
    -0.72
     can
    -0.71
     will
    -0.68
    .
    -0.68
    ,
    -0.68
     "
    -0.66
    POSITIVE LOGITS
     CreateTagHelper
    1.45
     صوتيه
    1.28
     виправивши
    1.25
    tagHelperRunner
    1.23
    Autoritní
    1.20
     pinulongan
    1.20
     متعلقه
    1.18
    InjectAttribute
    1.15
    ⓧ
    1.11
     مرئيه
    1.09
    Activations Density 0.321%

    No Known Activations