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. 2-GEMMASCOPE-RES-16K
    6. 1180
    Prev
    Next
    INDEX
    Explanations

    instances of the word "wake" 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 @ 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
    localctx
    -0.75
    awtextra
    -0.75
    SharedCtor
    -0.73
    CrossRef
    -0.72
    يكب
    -0.67
    ToBounds
    -0.63
    Hochspringen
    -0.63
    CppMethod
    -0.62
     برانيه
    -0.60
    icao
    -0.59
    POSITIVE LOGITS
     wake
    3.63
     wakes
    3.12
     Wake
    3.07
    wake
    3.02
    Wake
    2.96
     waking
    2.80
     woke
    2.79
     woken
    2.66
    WAKE
    2.35
     awake
    2.10
    Activations Density 0.026%

    No Known Activations