© 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. 0-GEMMASCOPE-RES-16K
    11. 3001
    Prev
    Next
    INDEX
    Explanations

    markup language elements and their structures within the text

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_0/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.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -1.20
     faſt
    -1.10
     ſta
    -1.07
     auffi
    -1.05
     ſind
    -1.02
    ſelves
    -1.00
     ſever
    -1.00
     Reſ
    -1.00
     verſ
    -1.00
     indígen
    -1.00
    POSITIVE LOGITS
    <?
    1.30
     <
    1.21
    <>
    1.16
    <<
    1.15
     <?
    1.11
    <
    1.05
    <-
    1.00
     <<
    0.96
    <\
    0.94
     <-
    0.90
    Activations Density 0.704%

    No Known Activations