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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 7-GEMMASCOPE-RES-16K
    6. 14718
    Prev
    Next
    INDEX
    Explanations

    the symbol "&" and its variations in multiple contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Edg
    -0.72
    Discography
    -0.69
    Sü
    -0.69
     Ró
    -0.65
     GRAN
    -0.65
    Recur
    -0.65
     Stef
    -0.64
    มาะ
    -0.64
     Bala
    -0.63
     NTS
    -0.62
    POSITIVE LOGITS
     &
    1.44
     &=&
    1.13
    </th>
    1.07
    >&
    1.02
    :&
    1.00
    )&
    1.00
    %&
    0.97
    ">&
    0.96
    <h6>
    0.95
    *&
    0.95
    Activations Density 0.087%

    No Known Activations