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-2-9B
    4. Residual Stream - 131k
    5. 33-GEMMASCOPE-RES-131K
    6. 65887
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to measurement or assessment in scientific contexts

    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_33/width_131k/average_l0_91
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ModelExpression
    -0.61
     CreateTagHelper
    -0.56
    存于互联网档案馆
    -0.55
     ComVisible
    -0.54
    RenderAtEndOf
    -0.53
    ⓧ
    -0.53
     հղումներ
    -0.52
    PyExc
    -0.52
    OGND
    -0.52
    MarshalTo
    -0.52
    POSITIVE LOGITS
     vehicle
    0.58
     vessel
    0.55
     church
    0.53
     product
    0.52
     hotel
    0.49
     troop
    0.49
     aircraft
    0.48
     plant
    0.48
     device
    0.47
     Fahrzeug
    0.47
    Activations Density 0.426%

    No Known Activations