© 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. 3059
    Prev
    Next
    INDEX
    Explanations

    slang or informal terms related to relationships or interconnectedness

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

    The token "sl" (lowercase or uppercase)

    np_acts-logits-general · gemini-2.0-flash

    words starting with sl

    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
     resourceCulture
    -0.94
    ]--;
    -0.92
     doInBackground
    -0.87
    AndEndTag
    -0.86
    oneofs
    -0.78
    __':
    -0.77
    الإنجليزية
    -0.76
    GeneratedValue
    -0.71
    IntoConstraints
    -0.70
     فريبيس
    -0.68
    POSITIVE LOGITS
     sl
    0.77
     Slide
    0.67
     Slo
    0.67
     Slides
    0.67
     slides
    0.67
     Sl
    0.65
    slo
    0.64
     Sloan
    0.62
     slide
    0.62
     SL
    0.61
    Activations Density 0.096%

    No Known Activations