© 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. 8180
    Prev
    Next
    INDEX
    Explanations

    occurrences and references to interleukins, specifically IL-7, in various contexts

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

    "Il" followed by a letter

    np_acts-logits-general · gemini-2.0-flash

    IL- prefixes

    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
     cref
    -0.57
    TagMode
    -0.53
    URLException
    -0.52
     same
    -0.52
     exact
    -0.50
     EXACT
    -0.49
     oprot
    -0.49
    exact
    -0.48
     öff
    -0.47
    ształ
    -0.47
    POSITIVE LOGITS
    Geplaatst
    0.69
    AddTagHelper
    0.64
     Urbana
    0.63
    indd
    0.61
    httphttps
    0.61
    inois
    0.61
    setVerticalGroup
    0.60
     faut
    0.56
    WithIOException
    0.56
    iastes
    0.56
    Activations Density 0.127%

    No Known Activations