© 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. 21-GEMMASCOPE-RES-16K
    6. 3358
    Prev
    Next
    INDEX
    Explanations

    comparative and superlative terms indicating abundance or frequency

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pequenas
    -0.67
     pequenos
    -0.63
     malades
    -0.63
     réfugi
    -0.63
     gyhoeddwyd
    -0.63
    OGND
    -0.62
     destul
    -0.62
    Personensuche
    -0.61
    Muy
    -0.61
     buenas
    -0.60
    POSITIVE LOGITS
     than
    1.70
    than
    1.19
     THAN
    1.17
    Than
    1.10
     Than
    1.05
     niż
    1.02
    THAN
    0.86
     likely
    0.84
     než
    0.83
     importantly
    0.79
    Activations Density 0.178%

    No Known Activations