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. 3-GEMMASCOPE-RES-16K
    6. 10128
    Prev
    Next
    INDEX
    Explanations

    percentages or proportions expressed as "cent."

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelf
    -1.10
     Monfieur
    -1.08
     houſe
    -1.05
     pleaſure
    -1.01
     Perſ
    -0.98
     Houſe
    -0.95
     Diſ
    -0.94
     perſon
    -0.94
     Efq
    -0.93
     uſe
    -0.92
    POSITIVE LOGITS
     cent
    2.63
     Cent
    1.92
    Cent
    1.89
    cent
    1.88
     CENT
    1.45
     Centennial
    1.15
    CENT
    1.14
     cents
    1.11
     cento
    0.98
     Centurion
    0.95
    Activations Density 0.056%

    No Known Activations