Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 9809
    Prev
    Next
    INDEX
    Explanations

    special characters and formatting symbols in the text

    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
    tvguidetime
    -0.61
     copy
    -0.56
     defStyleAttr
    -0.54
    itiers
    -0.54
    LayoutStyle
    -0.52
     ContentValues
    -0.50
    ksesta
    -0.50
    ular
    -0.49
    getSubject
    -0.49
    yfikacja
    -0.48
    POSITIVE LOGITS
     nonatomic
    0.60
     inmobili
    0.58
    -\
    0.57
     BIBSYS
    0.56
     anatomical
    0.55
    loroethene
    0.55
    href
    0.54
     ISNI
    0.53
    TypedDataSet
    0.52
     décé
    0.52
    Activations Density 0.940%

    No Known Activations