© 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 - 131k
    9. 20-GEMMASCOPE-RES-131K
    11. 121203
    Prev
    Next
    INDEX
    Explanations

    the frequency of the word "to" in varying contexts

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

    degrees of comparison

    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-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
     judiciaire
    -0.51
     extérieures
    -0.50
     lisäksi
    -0.49
     laterales
    -0.49
     humaines
    -0.47
     vectorielles
    -0.47
     mensaj
    -0.47
     añadido
    -0.46
     provisoire
    -0.45
     pério
    -0.44
    POSITIVE LOGITS
    ngdoc
    0.79
    webElementXpaths
    0.77
    complexContent
    0.74
    Datuak
    0.68
    migrationBuilder
    0.67
     الرياضيه
    0.66
     unknownFields
    0.60
    Personendaten
    0.60
     noDo
    0.59
    aarrggbb
    0.58
    Activations Density 0.017%

    No Known Activations