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. 24-GEMMASCOPE-RES-16K
    6. 2231
    Prev
    Next
    INDEX
    Explanations

    instructions related to DIY or crafting projects

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Followed by "of," "a," or descriptive adjectives

    np_acts-logits-general · gemini-2.0-flash

    coloured items and containers

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    FAVOR
    -0.90
     neighborhood
    -0.89
     neighborhoods
    -0.89
     confiable
    -0.88
    favorite
    -0.88
    Favorite
    -0.87
    AVOR
    -0.85
     zijne
    -0.84
    Neighborhood
    -0.82
    ighborhood
    -0.81
    POSITIVE LOGITS
    Whilst
    1.25
     Whilst
    1.20
     whilst
    1.12
    initialise
    1.08
     Initialise
    1.01
     initialise
    0.98
     despatch
    0.98
     coloured
    0.97
     personalised
    0.96
     colour
    0.96
    Activations Density 0.275%

    No Known Activations