© 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. 12709
    Prev
    Next
    INDEX
    Explanations

    references to temperature-related organizations and events

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

    "Met" followed by various words

    np_acts-logits-general · gemini-2.0-flash

    Met compound words

    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
     '\\;'
    -0.55
     ExecuteAsync
    -0.54
     superiori
    -0.53
    WithFormat
    -0.52
    SpringBootTest
    -0.52
    InputTagHelper
    -0.51
    RefreshLayout
    -0.50
    mias
    -0.49
    gräns
    -0.49
    ลาย
    -0.49
    POSITIVE LOGITS
     AssemblyTitle
    0.73
     teller
    0.60
    ]--;
    0.56
     Métro
    0.53
    politan
    0.51
     Met
    0.50
    PerformLayout
    0.50
     Meto
    0.50
     Dade
    0.50
     MessageBoxIcon
    0.49
    Activations Density 0.162%

    No Known Activations