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. 7-GEMMASCOPE-RES-16K
    6. 6569
    Prev
    Next
    INDEX
    Explanations

    numerals and references to time or measurement related to healthcare 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
     transférez
    -0.99
    UrlResolution
    -0.97
    UnsafeEnabled
    -0.97
    SourceChecksum
    -0.95
    AddTagHelper
    -0.86
    oredCriteria
    -0.86
    webElementXpaths
    -0.86
    bootstrapcdn
    -0.85
    hoeddwyd
    -0.83
    WebVitals
    -0.83
    POSITIVE LOGITS
    -
    0.55
    cin
    0.40
    Canto
    0.40
    után
    0.40
    Obras
    0.39
     берегу
    0.39
     kling
    0.38
    ian
    0.38
     lado
    0.38
     felb
    0.37
    Activations Density 0.044%

    No Known Activations