© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 10-GEMMASCOPE-RES-16K
    6. 6079
    Prev
    Next
    INDEX
    Explanations

    instances of the word "yet" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 10-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_10/width_16k/average_l0_77
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.10.hook_resid_post
    Hook Layer
    10
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    a
    -0.75
    </b>
    -0.73
    </i>
    -0.73
    .
    -0.69
     Braxton
    -0.67
    ia
    -0.67
     Concordia
    -0.67
     control
    -0.64
    regas
    -0.63
    bum
    -0.63
    POSITIVE LOGITS
     YET
    1.03
     Yet
    0.99
    yet
    0.98
     yet
    0.94
    TestingModule
    0.93
     INTERESAR
    0.92
    Yet
    0.91
    theless
    0.90
     Chant
    0.86
     Elem
    0.82
    Activations Density 0.042%

    No Known Activations