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-2-9B
    4. Residual Stream - 16k
    5. 28-GEMMASCOPE-RES-16K
    6. 7950
    Prev
    Next
    INDEX
    Explanations

    instances of the word "that," indicating an emphasis on statements or assertions

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

    "that" followed by a determiner or preposition

    np_acts-logits-general · gemini-2.0-flash

    that introduces clause

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 28-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_28/width_16k/average_l0_119
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.28.hook_resid_post
    Hook Layer
    28
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    RenderAtEndOf
    -0.71
    
    -0.69
    CppMethod
    -0.65
    PMS
    -0.61
     IMC
    -0.57
    NameInMap
    -0.56
     للاسماء
    -0.56
     PMP
    -0.55
     PMS
    -0.55
     JT
    -0.55
    POSITIVE LOGITS
     there
    0.79
     it
    0.62
     the
    0.60
     they
    0.59
     meskipun
    0.52
    although
    0.49
     although
    0.49
    there
    0.46
     efectivamente
    0.45
     genellikle
    0.41
    Activations Density 0.402%

    No Known Activations