© 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. 27-GEMMASCOPE-RES-16K
    6. 10098
    Prev
    Next
    INDEX
    Explanations

    weather conditions and their descriptions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 27-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_27/width_16k/average_l0_118
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.27.hook_resid_post
    Hook Layer
    27
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     صوتيه
    -1.07
     Италијани
    -0.91
    rungsseite
    -0.77
     للمعارف
    -0.77
     informée
    -0.77
    tagHelperRunner
    -0.76
    majánló
    -0.74
     témoig
    -0.73
     Numerade
    -0.72
     ویکی‌آمباردا
    -0.71
    POSITIVE LOGITS
     rain
    0.56
     wind
    0.56
     overcast
    0.54
     windy
    0.51
     weather
    0.50
     winds
    0.46
     rainy
    0.43
     raining
    0.43
     sun
    0.42
     dry
    0.42
    Activations Density 0.165%

    No Known Activations