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 - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 461
    Prev
    Next
    INDEX
    Explanations

    mention of the term 'concept' in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Uang
    -0.48
     Emig
    -0.46
    Diary
    -0.45
    getFile
    -0.44
     CHLOR
    -0.42
    leak
    -0.42
     getFile
    -0.41
    roomId
    -0.41
    dgv
    -0.40
    InStock
    -0.40
    POSITIVE LOGITS
     Concept
    0.72
    concept
    0.71
    Concept
    0.70
     CONCEPT
    0.61
    sense
    0.59
     SENSE
    0.59
    aspects
    0.59
    concepts
    0.59
     concept
    0.59
    aspect
    0.59
    Activations Density 0.158%

    No Known Activations