© 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. 8-GEMMASCOPE-RES-16K
    11. 6421
    Prev
    Next
    INDEX
    Explanations

    expressions of approval or admiration for things that are considered "cool."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_8/width_16k/average_l0_99
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    OGND
    -0.29
     laiko
    -0.29
    发表于
    -0.28
     Or
    -0.27
     May
    -0.26
    nyataan
    -0.26
    NSIndexPath
    -0.26
    ähr
    -0.26
    PDOException
    -0.26
    はどこ
    -0.25
    POSITIVE LOGITS
     cool
    1.90
     coolest
    1.70
    Cool
    1.63
     Cool
    1.59
    cool
    1.55
     coolness
    1.48
     COOL
    1.48
    COOL
    1.42
     cooler
    1.27
     cools
    1.21
    Activations Density 0.180%

    No Known Activations