© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 5067
    Prev
    Next
    INDEX
    Explanations

    instances of the word "lack" and related phrases emphasizing shortages or deficiencies

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

    Absence or deficiency of something

    np_acts-logits-general · gemini-2.0-flash

    lack or absence of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_24/width_16k/average_l0_114
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndroidJUnit
    -0.47
    HttpEntity
    -0.47
     styled
    -0.45
     setOpen
    -0.45
    ☸
    -0.45
     MessageBoxIcon
    -0.43
    contentValues
    -0.43
    textField
    -0.43
    styled
    -0.43
     webView
    -0.42
    POSITIVE LOGITS
     lack
    0.91
     Lack
    0.81
    Lack
    0.81
     lacking
    0.76
     dearth
    0.75
     gebre
    0.71
     shortage
    0.69
     lacked
    0.68
     absence
    0.67
     falta
    0.66
    Activations Density 0.196%

    No Known Activations