Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 7-GEMMASCOPE-RES-16K
    6. 15488
    Prev
    Next
    INDEX
    Explanations

    time-related measurements, specifically focusing on seconds and minutes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_7/width_16k/average_l0_92
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     surla
    -0.33
    }{*}{}
    -0.28
    Referencies
    -0.28
    GeneratedValue
    -0.27
     estabiliz
    -0.26
     örgü
    -0.26
     Plan
    -0.26
    smt
    -0.25
     plán
    -0.25
     Gestão
    -0.24
    POSITIVE LOGITS
     seconds
    2.08
     Seconds
    1.89
    seconds
    1.84
    Seconds
    1.74
     Sekunden
    1.56
     SECON
    1.56
    SECONDS
    1.46
    secs
    1.45
     секунд
    1.44
     segundos
    1.41
    Activations Density 0.217%

    No Known Activations