© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 483
    Prev
    Next
    INDEX
    Explanations

    discussions around potential development and growth factors in a community context

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

    followed by a negative or limiting modifier

    np_acts-logits-general · gemini-2.0-flash

    limited or somewhat negative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     utterly
    -0.80
     completely
    -0.75
     totally
    -0.73
    DockStyle
    -0.71
     Completely
    -0.70
     enormously
    -0.69
     massively
    -0.69
     absolutamente
    -0.66
     absolutely
    -0.65
     insanely
    -0.65
    POSITIVE LOGITS
     somewhat
    1.25
     sometimes
    1.21
     slightly
    1.11
    somewhat
    1.11
    少々
    1.09
     agak
    1.08
     Somewhat
    1.07
    slightly
    1.06
     trochu
    1.05
     nieco
    1.04
    Activations Density 0.765%

    No Known Activations