Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 10400
    Prev
    Next
    INDEX
    Explanations

    information related to payment confirmations and account activity

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

    Followed by passive verbs

    np_acts-logits-general · gemini-2.0-flash

    processed or completed actions

    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
     GetEnumerator
    -0.66
    WriteAttribute
    -0.53
     noqa
    -0.52
    upassen
    -0.52
     YellowPages
    -0.52
    naio
    -0.52
     BitmapFactory
    -0.52
    XmlAccessorType
    -0.52
    donate
    -0.50
    RegressionTest
    -0.50
    POSITIVE LOGITS
     processing
    1.19
     processed
    1.17
     Processing
    1.12
    processing
    1.04
    Processing
    1.02
     Processed
    0.99
     PROCESSING
    0.96
    processed
    0.95
    Processed
    0.88
    PROCESSING
    0.85
    Activations Density 0.249%

    No Known Activations