Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 45568
    Prev
    Next
    INDEX
    Explanations

    scientific and technical terminology related to materials and food

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

    concrete nouns in descriptions

    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
    AddTagHelper
    -0.54
    Personendaten
    -0.47
    çalves
    -0.45
    InjectMocks
    -0.43
    Religious
    -0.43
    essive
    -0.42
    '],$
    -0.42
    ExtendWith
    -0.41
    恹
    -0.41
     houſe
    -0.41
    POSITIVE LOGITS
     iconTwitter
    0.44
    UrlResolution
    0.39
     ddelweddau
    0.36
    AnchorTagHelper
    0.34
     ento
    0.32
    loop
    0.32
     لينك
    0.32
     vPvB
    0.31
     الاطلاع
    0.31
     actionMode
    0.31
    Activations Density 0.066%

    No Known Activations