© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 17-GEMMASCOPE-RES-16K
    6. 9532
    Prev
    Next
    INDEX
    Explanations

    elements of programming class and method structure

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 17-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_17/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.17.hook_resid_post
    Hook Layer
    17
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ExtendWith
    -0.51
    arel
    -0.47
     ViewPager
    -0.46
    URLEncoder
    -0.46
     gevolg
    -0.45
    mpä
    -0.45
     fuß
    -0.45
    AutoresizingMask
    -0.45
     BorderRadius
    -0.44
     tiks
    -0.43
    POSITIVE LOGITS
     चीज़ों
    0.99
    \{\\
    0.83
    public
    0.83
    protected
    0.83
    static
    0.80
    private
    0.79
     للاسماء
    0.77
    TypedDataSet
    0.76
    GEBURTSDATUM
    0.74
    SharedCtor
    0.74
    Activations Density 0.139%

    No Known Activations