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

    Neuronpedia

    APICircuit 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. 20-GEMMASCOPE-RES-16K
    6. 12073
    Prev
    Next
    INDEX
    Explanations

    the presence of single quotation marks

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/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.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    новништво
    -0.64
    __':
    
    -0.64
    InjectAttribute
    -0.58
    $_['
    -0.57
    wpi
    -0.57
    AttributeSet
    -0.55
    WebServlet
    -0.55
    Comté
    -0.53
    Pranala
    -0.52
     Audiodateien
    -0.52
    POSITIVE LOGITS
    ńcu
    0.53
    chery
    0.52
    urcht
    0.52
    gridColumn
    0.51
     AdapterView
    0.50
    use
    0.49
     DBNull
    0.46
     Unt
    0.46
     düş
    0.45
     따
    0.45
    Activations Density 0.069%

    No Known Activations