© 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
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 22-GEMMASCOPE-RES-16K
    11. 3505
    Prev
    Next
    INDEX
    Explanations

    references to standards and protocols in various contexts

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

    "Standard" followed by error, protocol, or model

    np_acts-logits-general · gemini-2.0-flash

    standard deviation

    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
     initComponents
    -0.77
    ModelSerializer
    -0.72
    FFIC
    -0.71
     CreateTagHelper
    -0.70
     AssemblyTitle
    -0.69
    utilisons
    -0.68
     onPostExecute
    -0.67
    ($__
    -0.65
     resourceCulture
    -0.63
     postIndex
    -0.62
    POSITIVE LOGITS
     deviation
    1.06
    isation
    1.02
    Deviation
    0.88
     deviations
    0.87
     Deviation
    0.86
     bearers
    0.79
    deviation
    0.78
     bearer
    0.77
    ising
    0.73
     Chartered
    0.70
    Activations Density 0.071%

    No Known Activations