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. 14428
    Prev
    Next
    INDEX
    Explanations

    mentions of players and coaching staff in a sports context

    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
     honte
    -0.34
     porté
    -0.32
     meyd
    -0.32
    Lifecycle
    -0.29
     måde
    -0.29
    ائج
    -0.28
     desc
    -0.28
     Arch
    -0.27
     навчання
    -0.27
     personas
    -0.27
    POSITIVE LOGITS
     CreateTagHelper
    0.66
    tagHelperRunner
    0.64
    principalColumn
    0.64
    cipar
    0.60
    évaluateur
    0.58
    WebVitals
    0.56
    CppMethod
    0.55
    AISSEE
    0.52
     Roskov
    0.52
    enderror
    0.51
    Activations Density 0.107%

    No Known Activations