© 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-2-9B
    4. Residual Stream - 16k
    5. 3-GEMMASCOPE-RES-16K
    6. 8311
    Prev
    Next
    INDEX
    Explanations

    occurrences of the term "requested" in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_3/width_16k/average_l0_90
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     pleaſure
    -0.52
     faſt
    -0.49
    Portail
    -0.48
     deſt
    -0.47
     souci
    -0.46
    ConstraintMaker
    -0.45
    انتهای
    -0.45
     fulfilled
    -0.44
    Glej
    -0.43
    ValueStyle
    -0.42
    POSITIVE LOGITS
     requested
    1.91
    requested
    1.67
     Requested
    1.59
    Requested
    1.57
     demanded
    1.49
     complained
    1.40
     asked
    1.36
     questioned
    1.30
     Asked
    1.24
    asked
    1.17
    Activations Density 0.197%

    No Known Activations