© 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. 20-GEMMASCOPE-RES-16K
    11. 2496
    Prev
    Next
    INDEX
    Explanations

    phrases related to conditional requirements and outputs

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

    Code snippets and mixed language text

    np_acts-logits-general · gemini-2.0-flash

    technical documentation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     estekak
    -0.92
    
    -0.83
    WireFormatLite
    -0.72
    GEBURTS
    -0.72
     Paglinawan
    -0.71
    ailleurs
    -0.69
     farlo
    -0.66
     betweenstory
    -0.66
    ThroughAttribute
    -0.65
     AssemblyCulture
    -0.65
    POSITIVE LOGITS
     تضيفلها
    0.63
    seiti
    0.59
    zeiti
    0.58
    zeitige
    0.56
     بيها
    0.53
    </u>
    0.53
    ories
    0.50
    IFORN
    0.49
    issez
    0.48
    tain
    0.48
    Activations Density 0.759%

    No Known Activations