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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 2159
    Prev
    Next
    INDEX
    Explanations

    tabular or statistical representations of data

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     com
    -0.51
     getClass
    -0.50
    CollectionUtils
    -0.48
     waw
    -0.48
     Gandalf
    -0.47
     MainAxisSize
    -0.47
    :+:
    -0.47
    كتشاف
    -0.46
    propylene
    -0.46
    ntgen
    -0.46
    POSITIVE LOGITS
    WebVitals
    0.67
     ExecuteAsync
    0.66
    ंदीखरीदारी
    0.65
     שוליים
    0.63
    expandindo
    0.59
    WithMany
    0.56
     ويكيميديا
    0.55
    contentLoaded
    0.55
     chi̍t
    0.54
     AssemblyVersion
    0.54
    Activations Density 0.245%

    No Known Activations