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. 8707
    Prev
    Next
    INDEX
    Explanations

    indicators or references to regulatory frameworks or structured methodologies

    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
    tagHelperRunner
    -0.87
    oa̍t
    -0.84
    expandindo
    -0.79
    contentLoaded
    -0.77
    GetEnumerator
    -0.76
     '{@
    -0.74
     Administrativna
    -0.71
    RegistryLite
    -0.70
     Económica
    -0.70
    PerformLayout
    -0.67
    POSITIVE LOGITS
    FontStyle
    1.64
     MessageBoxIcon
    1.10
    CrossRef
    0.90
    FromArgb
    0.72
    makeText
    0.64
    EntityFramework
    0.63
    SEVERE
    0.62
     rgba
    0.59
     TextAlign
    0.58
    wertig
    0.54
    Activations Density 0.007%

    No Known Activations