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. 23-GEMMASCOPE-RES-131K
    6. 23126
    Prev
    Next
    INDEX
    Explanations

    phrases related to business motivations and justifications

    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_23/width_131k/average_l0_101
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    AndEndTag
    -0.36
    снаб
    -0.35
     MANUFACT
    -0.34
     commerce
    -0.33
     basal
    -0.33
     practicality
    -0.33
     com
    -0.33
     sínt
    -0.32
     verlassen
    -0.32
    ResId
    -0.32
    POSITIVE LOGITS
     NSCoder
    0.77
    Xna
    0.69
    MLLoader
    0.69
    tagHelperRunner
    0.67
     resourceCulture
    0.61
    AddTagHelper
    0.61
     qualitative
    0.60
    IndentedString
    0.60
    rrggbb
    0.58
     emotional
    0.56
    Activations Density 0.119%

    No Known Activations