© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-9B
    7. Residual Stream - 16k
    9. 21-GEMMASCOPE-RES-16K
    11. 14030
    Prev
    Next
    INDEX
    Explanations

    references and metrics related to database queries and structures

    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
    tagHelperRunner
    -1.01
    
    -0.75
     betweenstory
    -0.67
     <<<<<<<<<<<<<<
    -0.64
    parsedMessage
    -0.61
     Walkover
    -0.61
     كومونز
    -0.59
     الحره
    -0.58
     Meksiku
    -0.58
     surla
    -0.57
    POSITIVE LOGITS
     quantities
    0.47
     count
    0.46
    counts
    0.46
    的数量
    0.46
     counts
    0.46
     jumlah
    0.45
     quantity
    0.44
     numbers
    0.44
    数量
    0.43
    Jumlah
    0.42
    Activations Density 0.856%

    No Known Activations