© 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-2-9B-IT
    7. Residual Stream - 16k
    9. 20-GEMMASCOPE-RES-16K
    11. 1469
    Prev
    Next
    INDEX
    Explanations

    references to content or information that is located elsewhere in the text, typically indicated by the word "below."

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

    "below"

    np_acts-logits-general · gemini-2.0-flash

    referring to following content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_16k/average_l0_91
    Prompts (Dashboard)
    24,576 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
     AssemblyTitle
    -0.84
    دانشنامهٔ
    -0.69
     AssemblyVersion
    -0.68
     NavController
    -0.60
    ագրություններ
    -0.59
    ()");
    -0.56
    GEBURTSDATUM
    -0.56
    "];
    -0.56
    )");
    -0.56
    >\<^
    -0.55
    POSITIVE LOGITS
     below
    0.90
    Below
    0.79
     Below
    0.79
    below
    0.75
     abaixo
    0.69
     hieronder
    0.63
     nedan
    0.62
     bellow
    0.62
     ниже
    0.61
     continuación
    0.59
    Activations Density 0.427%

    No Known Activations