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. 2067
    Prev
    Next
    INDEX
    Explanations

    the beginning or initialization markers in the document

    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
    SharedCtor
    -0.83
    IsMutable
    -0.69
    TintMode
    -0.68
    titleMargin
    -0.67
    PreferredItem
    -0.65
    SerializedSize
    -0.64
     …
    -0.62
    rrggbb
    -0.62
    PerformLayout
    -0.61
    WireFormatLite
    -0.60
    POSITIVE LOGITS
    tagHelperRunner
    0.84
    <bos>
    0.76
     pylint
    0.73
     للمعارف
    0.68
     ddelweddau
    0.66
    Дереккөздер
    0.64
     *
    
    
    0.63
    évaluateur
    0.63
     snippetHide
    0.63
     tfsi
    0.61
    Activations Density 0.033%

    No Known Activations