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
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 114947
    Prev
    Next
    INDEX
    Explanations

    references to personal development and past experiences of individuals

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_131k/average_l0_114
    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
    CloseOperation
    -0.49
     nonatomic
    -0.49
    ptăm
    -0.47
    ValueGeneration
    -0.45
    jspx
    -0.45
    RequestMapping
    -0.44
    astify
    -0.43
    rawDesc
    -0.42
     Ketten
    -0.42
    AddTagHelper
    -0.41
    POSITIVE LOGITS
    évaluateur
    0.45
     hervorge
    0.38
     oorsp
    0.36
    本身
    0.34
    InitVars
    0.34
    WriteTagHelper
    0.33
     énon
    0.33
    گاب
    0.33
     leef
    0.33
    BeginContext
    0.33
    Activations Density 0.032%

    No Known Activations