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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 12308
    Prev
    Next
    INDEX
    Explanations

    terms related to space exploration and astronauts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_10/width_16k/average_l0_113
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    zeit
    -0.33
     šķ
    -0.32
    TRY
    -0.30
     primary
    -0.30
    呈
    -0.29
    amil
    -0.28
    Coordonnées
    -0.28
    primary
    -0.28
    TableView
    -0.28
    ruppe
    -0.27
    POSITIVE LOGITS
     EconPapers
    0.79
     ſind
    0.75
     anſ
    0.70
     ſche
    0.70
     Anſ
    0.67
     ſei
    0.66
    AndEndTag
    0.65
     ISTAT
    0.62
     astronauts
    0.60
     viſ
    0.59
    Activations Density 0.297%

    No Known Activations