© 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. 2-GEMMASCOPE-RES-16K
    6. 786
    Prev
    Next
    INDEX
    Explanations

    the word "saying" and its variations, indicating discussions or declarations made by individuals

    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
    èze
    -0.61
     spel
    -0.53
    ValueGeneration
    -0.50
    =$_
    -0.47
    しかった
    -0.47
    ǒ
    -0.46
     Hughes
    -0.46
    siao
    -0.46
    mest
    -0.46
     useNavigate
    -0.46
    POSITIVE LOGITS
     saying
    2.80
    saying
    2.39
     Saying
    2.32
    Saying
    2.26
     sayin
    1.97
     diciendo
    1.91
     stating
    1.89
     dizendo
    1.72
     dicendo
    1.52
     telling
    1.38
    Activations Density 0.115%

    No Known Activations