© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 2482
    Prev
    Next
    INDEX
    Explanations

    Roman numerals and related numerical categorization

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_1/width_16k/average_l0_69
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     виправивши
    -0.47
     Anspruch
    -0.44
     whipping
    -0.42
    solved
    -0.41
    ApiModel
    -0.40
    SourceChecksum
    -0.40
     Saif
    -0.39
    ItemModel
    -0.39
    PostMapping
    -0.39
     Lí
    -0.38
    POSITIVE LOGITS
     VIII
    1.14
    VIII
    1.13
     XIII
    1.07
     XVI
    1.03
    XIII
    0.99
     XVIII
    0.98
     thirteenth
    0.96
    XVIII
    0.95
     VII
    0.95
     XII
    0.94
    Activations Density 0.232%

    No Known Activations