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. 4-GEMMASCOPE-RES-16K
    6. 15873
    Prev
    Next
    INDEX
    Explanations

    HTML links and buttons 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 @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    tvguidetime
    -1.10
    GEBURTSDATUM
    -1.10
    XmlAccessorType
    -1.02
     تانيه
    -0.91
     itſelf
    -0.88
     pleaſure
    -0.88
     purpoſe
    -0.85
    SequentialGroup
    -0.85
    providedIn
    -0.85
     Conſ
    -0.85
    POSITIVE LOGITS
    a
    1.17
     href
    0.99
    NavLink
    0.84
    A
    0.79
    Link
    0.73
     Link
    0.72
     link
    0.67
     A
    0.66
    href
    0.65
    link
    0.61
    Activations Density 0.068%

    No Known Activations