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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 7135
    Prev
    Next
    INDEX
    Explanations

    the letter 'd' in various contexts, particularly at the endings of words

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ters
    -0.59
    DropColumn
    -0.56
    parsedMessage
    -0.55
     coincides
    -0.55
    lables
    -0.54
    NOPQRST
    -0.54
    ispo
    -0.53
    preneurship
    -0.51
    DoubleQuotes
    -0.51
    cifix
    -0.51
    POSITIVE LOGITS
     wouldn
    0.87
    d
    0.87
     had
    0.86
     would
    0.85
     WOULD
    0.85
     Would
    0.84
    Would
    0.82
     been
    0.80
    ve
    0.79
    wouldn
    0.79
    Activations Density 0.078%

    No Known Activations