© 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. 3-GEMMASCOPE-RES-16K
    6. 13220
    Prev
    Next
    INDEX
    Explanations

    the word "couldn't" and its variations, indicating a focus on negations related to abilities or possibilities

    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
    astie
    -0.77
    spesies
    -0.76
    HomeAsUpEnabled
    -0.75
     isEmpty
    -0.69
    jboss
    -0.69
     setIs
    -0.68
    stdc
    -0.68
    Obrázky
    -0.67
    strix
    -0.66
     bukanlah
    -0.63
    POSITIVE LOGITS
     couldn
    2.07
     Couldn
    1.89
    couldn
    1.83
    Couldn
    1.66
     couldnt
    1.38
     wouldn
    0.96
     cant
    0.95
    Cant
    0.95
     CANT
    0.91
     Cant
    0.90
    Activations Density 0.051%

    No Known Activations