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. 20-GEMMASCOPE-RES-16K
    6. 12927
    Prev
    Next
    INDEX
    Explanations

    statements of existence or presence

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     يتيمه
    -0.74
     Sodom
    -0.69
    OGND
    -0.64
    WithIOException
    -0.64
    NgModule
    -0.63
    IContainer
    -0.62
    DockStyle
    -0.62
     defaultstate
    -0.61
    ScopeManager
    -0.61
     EconPapers
    -0.60
    POSITIVE LOGITS
     the
    1.10
     a
    1.06
     actually
    0.89
     either
    0.88
     also
    0.84
     an
    0.83
     comprised
    0.81
     supposed
    0.79
     meant
    0.74
     berupa
    0.71
    Activations Density 0.682%

    No Known Activations