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. 15-GEMMASCOPE-RES-16K
    6. 5094
    Prev
    Next
    INDEX
    Explanations

    concerns about data privacy and security related to electronic communications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 15-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_15/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Hook Layer
    15
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     uiteindelijk
    -0.49
     देखें
    -0.48
     discussione
    -0.47
    dann
    -0.46
    FieldError
    -0.46
     MainAxisSize
    -0.46
    webElement
    -0.46
    webElementGuid
    -0.45
    Thankfully
    -0.44
     Maret
    -0.44
    POSITIVE LOGITS
     want
    1.10
     wanted
    1.03
     wants
    0.99
     Want
    0.94
     need
    0.93
     Need
    0.92
    want
    0.87
     Wants
    0.87
    Need
    0.85
    Want
    0.82
    Activations Density 0.388%

    No Known Activations