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. 16-GEMMASCOPE-RES-16K
    6. 12842
    Prev
    Next
    INDEX
    Explanations

    phrases related to averages and statistical measures

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_16/width_16k/average_l0_75
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    investissement
    -0.43
    Scotland
    -0.43
     longtemps
    -0.42
     acción
    -0.41
    촉
    -0.40
     FileNotFound
    -0.39
     tamamen
    -0.38
    tshell
    -0.38
     düğ
    -0.38
    Зак
    -0.38
    POSITIVE LOGITS
     Average
    1.30
    Average
    1.26
     average
    1.26
    average
    1.25
     AVERAGE
    1.23
     Avg
    1.16
    AVERAGE
    1.12
     avg
    1.09
    Avg
    1.06
    AVG
    1.05
    Activations Density 0.101%

    No Known Activations