© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 12-GEMMASCOPE-RES-16K
    6. 5801
    Prev
    Next
    INDEX
    Explanations

    expressions related to time and measurement, particularly those involving frequency or amounts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 12-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_12/width_16k/average_l0_130
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.12.hook_resid_post
    Hook Layer
    12
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    出版年
    -0.84
    bootstrapcdn
    -0.69
    
    -0.65
    GEBURTSDATUM
    -0.64
     mijne
    -0.64
    ⤹
    -0.62
    +#+#
    -0.61
    genodigd
    -0.61
     Comprometido
    -0.60
    httphttps
    -0.60
    POSITIVE LOGITS
     simult
    0.40
    Monthly
    0.38
     daily
    0.38
    Daily
    0.37
     fast
    0.37
    Fast
    0.36
    PerSecond
    0.36
     Excelsior
    0.35
     pir
    0.35
    sizePolicy
    0.35
    Activations Density 0.296%

    No Known Activations