© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 16-GEMMASCOPE-RES-16K
    11. 11681
    Prev
    Next
    INDEX
    Explanations

    comparisons and contrasts between different methods or experiences

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

    "Different" followed by a noun

    np_acts-logits-general · gemini-2.0-flash

    difference and variety

    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
    ότητα
    -0.50
     [*]
    -0.47
    ρες
    -0.40
    ̷
    -0.40
    ող
    -0.40
    ix
    -0.40
    ές
    -0.40
    配
    -0.39
    AGAN
    -0.39
    elt
    -0.39
    POSITIVE LOGITS
     different
    1.05
    different
    0.96
    Different
    0.93
     differing
    0.92
     Different
    0.89
     depending
    0.86
    各有
    0.85
     unterschied
    0.84
     différent
    0.84
    不同的
    0.82
    Activations Density 0.401%

    No Known Activations