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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 14263
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and expressions related to formal definitions or equations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ValueStyle
    -0.40
     crossorigin
    -0.40
    ❋
    -0.36
    綜合報導
    -0.35
     ơn
    -0.33
     equalTo
    -0.32
     fucking
    -0.31
    대한
    -0.31
     prakty
    -0.31
    IsPostBack
    -0.30
    POSITIVE LOGITS
    parsedMessage
    0.75
    OGND
    0.72
    SourceChecksum
    0.61
    MessageOf
    0.60
    +#+#
    0.58
     fieldNum
    0.52
     oprot
    0.52
     intStringLen
    0.51
     betweenstory
    0.51
    featureID
    0.51
    Activations Density 14.390%

    No Known Activations