© 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-2-2B
    7. Residual Stream - 16k
    9. 25-GEMMASCOPE-RES-16K
    11. 2949
    Prev
    Next
    INDEX
    Explanations

    phrases indicating time references

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    references to time, particularly phrases indicating recent timeframes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    GEBURTSDATUM
    -0.79
     للمعارف
    -0.68
     оригіналу
    -0.60
     незавершена
    -0.60
    rrggbb
    -0.59
     فريبيس
    -0.59
     صوتيه
    -0.57
    庁
    -0.55
    addGap
    -0.53
    RepeatedField
    -0.53
    POSITIVE LOGITS
     few
    1.63
     couple
    1.32
    few
    1.17
     several
    0.99
    Few
    0.96
    couple
    0.93
     decade
    0.92
     handful
    0.91
     Few
    0.90
     FEW
    0.89
    Activations Density 0.172%

    No Known Activations