© 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. 2-GEMMASCOPE-RES-16K
    6. 9109
    Prev
    Next
    INDEX
    Explanations

    instances of the word "however."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ">$
    -0.66
     ?";
    -0.63
    ziesz
    -0.62
     }}">
    -0.60
    ()?;
    -0.59
    ota
    -0.59
    }}}{
    -0.59
    '));
    -0.59
     Morton
    -0.58
    ():
    -0.58
    POSITIVE LOGITS
     however
    3.63
    however
    3.26
     entanto
    2.76
     However
    2.65
    However
    2.63
     però
    2.15
     cependant
    2.08
     porém
    2.05
     tuttavia
    2.05
     obstante
    1.97
    Activations Density 0.113%

    No Known Activations