© 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. 2-GEMMASCOPE-RES-16K
    6. 12654
    Prev
    Next
    INDEX
    Explanations

    instances of the word "great" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_2/width_16k/average_l0_67
    Prompts (Dashboard)
    24,576 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
    fjspx
    -0.56
    колеп
    -0.49
    Ligações
    -0.49
    tanleria
    -0.49
    IntoConstraints
    -0.49
    loem
    -0.48
    houette
    -0.47
    ambul
    -0.46
    yntaxException
    -0.44
    клопе
    -0.44
    POSITIVE LOGITS
     great
    3.69
    great
    3.41
    Great
    2.97
     Great
    2.88
     GREAT
    2.81
    GREAT
    2.77
     greate
    1.91
     grande
    1.78
     greats
    1.77
     вели
    1.71
    Activations Density 0.129%

    No Known Activations