Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 15042
    Prev
    Next
    INDEX
    Explanations

    references to educational institutions and academic achievements

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 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
    CppCodeGen
    -0.51
     drin
    -0.51
    anneer
    -0.47
    GetAxis
    -0.46
     patient
    -0.44
     retr
    -0.43
    Routine
    -0.42
     Obrador
    -0.42
    Anas
    -0.41
    structure
    -0.40
    POSITIVE LOGITS
     college
    0.98
     colleges
    0.93
     College
    0.90
     institute
    0.89
     university
    0.88
    college
    0.86
     universities
    0.85
     Collage
    0.84
    College
    0.81
     collage
    0.81
    Activations Density 0.189%

    No Known Activations