© 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. 13651
    Prev
    Next
    INDEX
    Explanations

    information related to reliability and efficiency in power supply systems

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

    system failure and reliability

    np_acts-logits-general · gemini-2.0-flash

    equipment failures and faults

    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
     ModelExpression
    -0.74
    enumii
    -0.57
    Kjelder
    -0.57
    ArgsConstructor
    -0.54
    $​
    -0.53
    EndContext
    -0.53
    kani
    -0.52
     Exactos
    -0.50
    onAttach
    -0.50
    EndInit
    -0.49
    POSITIVE LOGITS
     failure
    1.28
     failures
    1.18
     fault
    1.18
     Failure
    1.06
     fail
    1.05
    failure
    1.05
    fault
    1.03
     faults
    0.98
    Failure
    0.96
     Fault
    0.94
    Activations Density 0.608%

    No Known Activations