© 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. 33-GEMMASCOPE-RES-16K
    11. 130
    Prev
    Next
    INDEX
    Explanations

    mentions of various legal and situational factors affecting decisions or outcomes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 33-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_33/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.33.hook_resid_post
    Hook Layer
    33
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Архівовано
    -0.57
     مرئيه
    -0.50
     iprot
    -0.46
    TagMode
    -0.45
    참고
    -0.43
    ponses
    -0.42
    onActivityResult
    -0.41
    InjectAttribute
    -0.40
     endregion
    -0.40
    发表于
    -0.40
    POSITIVE LOGITS
     circumstances
    2.39
     Circumstances
    2.05
    circum
    1.97
     circonstances
    1.88
    Circum
    1.84
     circumstance
    1.78
     circunstancias
    1.73
     обстоятельства
    1.52
     CIRC
    1.50
     Circum
    1.50
    Activations Density 0.582%

    No Known Activations