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. 23-GEMMASCOPE-RES-16K
    6. 8900
    Prev
    Next
    INDEX
    Explanations

    references to sports teams and their performances

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    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
     cherchés
    -0.59
     arbol
    -0.45
    arium
    -0.40
    DRY
    -0.40
     DRY
    -0.40
    csol
    -0.40
    ocument
    -0.40
    Dry
    -0.40
    YE
    -0.39
    ⓧ
    -0.39
    POSITIVE LOGITS
     beat
    1.50
     beating
    1.35
     defeating
    1.27
     beats
    1.26
     defeated
    1.26
     beaten
    1.21
    beat
    1.20
    beats
    1.10
     Beat
    1.10
     BEAT
    1.10
    Activations Density 0.127%

    No Known Activations