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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 8-GEMMASCOPE-RES-16K
    6. 2051
    Prev
    Next
    INDEX
    Explanations

    the word "yet" and its variants, indicating a contrast or continuation in ideas

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 8-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_8/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.8.hook_resid_post
    Hook Layer
    8
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    </b>
    -0.85
    a
    -0.80
    </i>
    -0.76
    .
    -0.71
    PRO
    -0.69
     PRO
    -0.69
    ia
    -0.67
     Crusoe
    -0.66
    》
    -0.64
    hwa
    -0.63
    POSITIVE LOGITS
     YET
    1.10
     Yet
    1.08
    yet
    1.04
     yet
    1.03
    Yet
    0.98
     INTERESAR
    0.98
    TestingModule
    0.95
    theless
    0.95
    GEBURTSDATUM
    0.92
     GetEnumerator
    0.91
    Activations Density 0.040%

    No Known Activations