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. 6240
    Prev
    Next
    INDEX
    Explanations

    the verb "go" in various forms and 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
    MemoryWarning
    -0.79
     насељу
    -0.70
     ExecuteAsync
    -0.59
     Arkivert
    -0.57
    ValueStyle
    -0.56
     obiet
    -0.55
     niem
    -0.54
     itſelf
    -0.52
    хьтан
    -0.51
     myſelf
    -0.50
    POSITIVE LOGITS
     go
    3.88
    Go
    3.40
    go
    3.35
     Go
    3.32
     GO
    3.06
    GO
    2.86
     goes
    2.85
    goes
    2.62
     Goes
    2.40
     went
    2.31
    Activations Density 0.067%

    No Known Activations