© 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. 36-GEMMASCOPE-RES-16K
    11. 15875
    Prev
    Next
    INDEX
    Explanations

    phrases related to making informed decisions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 36-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_36/width_16k/average_l0_120
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.36.hook_resid_post
    Hook Layer
    36
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     للاسماء
    -0.46
    __*/
    -0.46
     Италијани
    -0.42
     חיצוניים
    -0.42
     ویکی‌پدیا
    -0.41
    ModelAdmin
    -0.40
    Bakgrunnsstoff
    -0.40
    Mechanisms
    -0.40
     OnEnable
    -0.39
     blumen
    -0.39
    POSITIVE LOGITS
     decision
    3.59
     decisions
    3.23
    decision
    3.13
     Decision
    2.92
    Decision
    2.91
     Decisions
    2.80
    decisions
    2.73
     décision
    2.72
     DECISION
    2.72
    Decisions
    2.70
    Activations Density 1.116%

    No Known Activations