© 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-2-2B
    4. Residual Stream - 16k
    5. 22-GEMMASCOPE-RES-16K
    6. 8236
    Prev
    Next
    INDEX
    Explanations

    phrases indicating necessity or importance

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

    Comes before adjectives of importance or usefulness

    np_acts-logits-general · gemini-2.0-flash

    it is important

    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
    tagHelperRunner
    -0.77
    QMetaType
    -0.75
    findpost
    -0.75
     Efq
    -0.72
     Eſ
    -0.66
     AssemblyTitle
    -0.65
    UnusedPrivate
    -0.65
     Anſ
    -0.64
     nahilalakip
    -0.62
    Tikang
    -0.61
    POSITIVE LOGITS
     best
    1.27
     advisable
    1.11
     wise
    1.03
    best
    1.03
     wisest
    1.02
     prudent
    0.98
     smartest
    0.94
     recommended
    0.92
     advised
    0.91
     safest
    0.91
    Activations Density 0.193%

    No Known Activations