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-2-2B
    4. Residual Stream - 16k
    5. 16-GEMMASCOPE-RES-16K
    6. 14856
    Prev
    Next
    INDEX
    Explanations

    numeric sequences and data representations

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

    The number 4

    np_acts-logits-general · gemini-2.0-flash

    4

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 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
    %)$
    -0.90
     изъ
    -0.81
    [--
    -0.81
     GetEnumerator
    -0.79
    alaya
    -0.79
     Wirt
    -0.79
    ificance
    -0.78
    исленность
    -0.78
    ValueStyle
    -0.78
     Bourgoin
    -0.77
    POSITIVE LOGITS
    4
    1.52
     @"/
    1.19
    5
    0.97
     Fournier
    0.85
    FOUR
    0.84
     FOUR
    0.83
    four
    0.83
     Four
    0.80
    6
    0.79
    8
    0.78
    Activations Density 1.114%

    No Known Activations