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. 21-GEMMASCOPE-RES-16K
    6. 341
    Prev
    Next
    INDEX
    Explanations

    references to authorship or attribution in texts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    VersionUID
    -0.51
     amarela
    -0.50
    getvalue
    -0.49
     étrangères
    -0.47
    bewerken
    -0.47
    istic
    -0.45
    bbero
    -0.45
     Hanford
    -0.45
    GraphicsUnit
    -0.44
     بندی
    -0.44
    POSITIVE LOGITS
     means
    1.59
     virtue
    1.41
     way
    1.31
    standers
    1.31
    means
    1.29
     MEANS
    1.17
    stander
    1.12
    Means
    1.07
     dint
    1.05
     Means
    1.03
    Activations Density 0.333%

    No Known Activations