© 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. 16-GEMMASCOPE-RES-16K
    6. 3429
    Prev
    Next
    INDEX
    Explanations

    past experiences or historical references related to specific subjects

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

    past times

    np_acts-logits-general · gemini-2.0-flash

    past state or time

    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
    PerformLayout
    -0.83
    ValueStyle
    -0.74
     الرياضيه
    -0.72
     kasarigan
    -0.69
     ddelweddau
    -0.68
    äldrar
    -0.68
    __':
    
    -0.66
     ostavi
    -0.66
    ército
    -0.66
     linkovi
    -0.64
    POSITIVE LOGITS
     ago
    0.69
     autrefois
    0.55
     before
    0.55
    ImageContext
    0.55
     früher
    0.54
    頃は
    0.51
     раньше
    0.49
     dulu
    0.48
    Before
    0.48
    fore
    0.47
    Activations Density 0.321%

    No Known Activations