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-2-9B
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 105341
    Prev
    Next
    INDEX
    Explanations

    terms related to biological testing and sample analysis

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    帖最后由
    -0.61
    Diweddarwch
    -0.52
     slips
    -0.44
     PARSER
    -0.42
     чесно
    -0.41
     Pen
    -0.41
     विश्वसनीयता
    -0.40
     cons
    -0.40
    Point
    -0.39
    jetty
    -0.39
    POSITIVE LOGITS
    EDEFAULT
    0.53
     autorytatywna
    0.53
     Normdatei
    0.50
    oa̍t
    0.48
    хьтан
    0.47
     BrowserModule
    0.47
    rawDesc
    0.46
     jspb
    0.45
    astéro
    0.44
    GeneratedMessage
    0.44
    Activations Density 0.282%

    No Known Activations