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. 29867
    Prev
    Next
    INDEX
    Explanations

    elements related to crafting and creative projects

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

    introduces 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
     mergeFrom
    -0.50
     SqlCommand
    -0.49
    esModule
    -0.48
     ApiException
    -0.45
    WriteBarrier
    -0.43
    fjspx
    -0.41
     >=",
    -0.41
     protoimpl
    -0.39
    addContainerGap
    -0.38
    TagMode
    -0.37
    POSITIVE LOGITS
     defaultstate
    0.57
     ujednoznacz
    0.46
    gelopen
    0.46
     eksemp
    0.44
    ponses
    0.44
    uação
    0.44
     suun
    0.43
    翻攝
    0.43
    edade
    0.43
    ácara
    0.43
    Activations Density 0.021%

    No Known Activations