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. 7522
    Prev
    Next
    INDEX
    Explanations

    verbs related to creating, improving, or making changes

    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
    getColumnIndex
    -0.60
    NameInMap
    -0.56
    SourceChecksum
    -0.54
     disambiguazione
    -0.52
    djangoproject
    -0.51
    thâu
    -0.50
     defaultstate
    -0.48
    RuleContext
    -0.47
     השאלה
    -0.47
     jenner
    -0.47
    POSITIVE LOGITS
     sure
    0.86
     informed
    0.72
     strides
    0.71
     lasting
    0.71
     Informed
    0.67
     connections
    0.66
     amends
    0.61
     improvements
    0.61
    lasting
    0.61
    connections
    0.60
    Activations Density 0.075%

    No Known Activations