Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 13864
    Prev
    Next
    INDEX
    Explanations

    the word "stop" and its variations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    <?
    -0.63
    KommentareTeilen
    -0.56
    getMenuInflater
    -0.50
    PMailer
    -0.50
    sphase
    -0.49
    acuzzi
    -0.48
    tvguidetime
    -0.47
     indisponible
    -0.46
    ]))
    
    -0.46
    ocino
    -0.46
    POSITIVE LOGITS
     stop
    4.67
     Stop
    4.45
    stop
    4.36
    Stop
    4.33
     stops
    4.19
     STOP
    3.99
     Stops
    3.85
    STOP
    3.84
     stopped
    3.74
    stops
    3.73
    Activations Density 0.060%

    No Known Activations