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. 8205
    Prev
    Next
    INDEX
    Explanations

    occurrences of the abbreviation "TP" or similar variations related to specific terminologies in a technical or scientific context

    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
    beforeAll
    -0.55
     keber
    -0.54
     dezelve
    -0.54
    GrantedAuthority
    -0.53
     zijne
    -0.53
     ogrodow
    -0.52
     actuels
    -0.52
     gustó
    -0.50
     récentes
    -0.50
     tijden
    -0.49
    POSITIVE LOGITS
     TP
    1.20
    TP
    1.12
     tp
    1.04
    tp
    0.96
     Tp
    0.89
    Tp
    0.85
     TPP
    0.79
     CTP
    0.76
     TPA
    0.74
     TPU
    0.71
    Activations Density 0.011%

    No Known Activations