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. 22-GEMMASCOPE-RES-16K
    6. 7964
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize quality and reliability in services and products

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

    Follows "our"

    np_acts-logits-general · gemini-2.0-flash

    our data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 22-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_22/width_16k/average_l0_72
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.22.hook_resid_post
    Hook Layer
    22
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    WebServlet
    -0.68
    ImageContext
    -0.66
    ########.
    -0.64
    sizeCache
    -0.60
    mybatisplus
    -0.59
    needed
    -0.53
    indest
    -0.52
    Hymen
    -0.52
     StringTokenizer
    -0.51
     الدولى
    -0.51
    POSITIVE LOGITS
     team
    1.03
     commitment
    0.92
     unique
    0.91
     experienced
    0.87
     dedication
    0.86
     extensive
    0.86
     range
    0.84
     diverse
    0.83
     comprehensive
    0.82
     versatile
    0.82
    Activations Density 0.139%

    No Known Activations