© 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. 7243
    Prev
    Next
    INDEX
    Explanations

    references to legal or regulatory rules and guidelines

    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
    setVerticalGroup
    -0.66
    SBATCH
    -0.65
    desertcart
    -0.61
    StructEnd
    -0.58
     betweenstory
    -0.57
     '\\;'
    -0.57
    évaluateur
    -0.57
     autorytatywna
    -0.56
    Hentet
    -0.54
     spamming
    -0.53
    POSITIVE LOGITS
     rule
    1.40
    rule
    1.25
    Rule
    1.20
     Rule
    1.13
     rules
    1.01
     RULE
    0.97
     ruled
    0.91
     Eng
    0.91
     English
    0.91
    RULE
    0.90
    Activations Density 0.220%

    No Known Activations