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. 3-GEMMASCOPE-RES-16K
    6. 6207
    Prev
    Next
    INDEX
    Explanations

    expressions of perception or feeling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    
    -0.77
     Alvarado
    -0.73
    णि
    -0.69
    toplankton
    -0.67
     friable
    -0.65
     Brito
    -0.65
    Zeneca
    -0.64
     McGuire
    -0.63
    burton
    -0.63
     Woodward
    -0.63
    POSITIVE LOGITS
     sense
    3.23
     Sense
    2.97
    sense
    2.87
     SENSE
    2.83
    Sense
    2.60
     senses
    2.18
     senso
    1.79
     Senses
    1.74
     sentido
    1.70
     sensed
    1.69
    Activations Density 0.055%

    No Known Activations