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. 7049
    Prev
    Next
    INDEX
    Explanations

    mathematical concepts and their relationships in formal language

    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
    AccessorTable
    -0.54
     مشين
    -0.51
    UnknownFieldSet
    -0.50
    WireFormatLite
    -0.47
     الرياضيه
    -0.44
    TestingModule
    -0.40
     상세
    -0.40
     HasFactory
    -0.40
    новништво
    -0.39
    ArrowToggle
    -0.38
    POSITIVE LOGITS
    InjectMocks
    0.49
     decorados
    0.43
     Pollution
    0.43
    argento
    0.43
     Besides
    0.43
     pingente
    0.43
    nytt
    0.42
     rilass
    0.42
     bezig
    0.42
     Economy
    0.42
    Activations Density 1.145%

    No Known Activations