© 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-2-2B
    4. Residual Stream - 16k
    5. 2-GEMMASCOPE-RES-16K
    6. 15394
    Prev
    Next
    INDEX
    Explanations

    affirmations and conclusions in discussions or narratives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     =>
    
    -0.46
     meist
    -0.45
    蹤
    -0.44
     ít
    -0.41
     различ
    -0.40
    extra
    -0.40
    wną
    -0.39
     собою
    -0.39
    meen
    -0.39
    tectable
    -0.39
    POSITIVE LOGITS
    تقاوى
    0.89
     <<<<<<<<<<<<<<
    0.82
     autorytatywna
    0.82
    VersionUID
    0.82
     Disclaimer
    0.81
    CLAIMER
    0.81
     bref
    0.80
     BTW
    0.80
    kháu
    0.80
     الرياضيه
    0.80
    Activations Density 0.582%

    No Known Activations