© 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. 16311
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate missed opportunities or things that are overlooked

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

    missing something

    np_acts-logits-general · gemini-2.0-flash

    missing out or missed opportunities

    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
    \}\\
    -0.59
    AndroidJUnit
    -0.55
     труда
    -0.55
    oredCriteria
    -0.54
    anyahu
    -0.54
    respectively
    -0.51
    ViewFeatures
    -0.50
    WebMethod
    -0.50
    elif
    -0.50
    dientemente
    -0.49
    POSITIVE LOGITS
     missed
    1.02
    Missed
    0.98
     Missed
    0.98
     misses
    0.94
     MISSING
    0.91
     MISS
    0.90
    teps
    0.87
    missed
    0.87
    tep
    0.86
     Misses
    0.81
    Activations Density 0.079%

    No Known Activations