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. 8436
    Prev
    Next
    INDEX
    Explanations

    phrases and terms related to statistical data and over-the-counter products

    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
     ſtate
    -0.96
     pleaſure
    -0.93
     neceff
    -0.83
     ftate
    -0.80
     whoſe
    -0.77
     houſe
    -0.75
     Majefty
    -0.75
     Efq
    -0.74
     poffe
    -0.73
     deſt
    -0.73
    POSITIVE LOGITS
     over
    1.01
     Over
    0.88
    Over
    0.80
     OVER
    0.75
    over
    0.67
     través
    0.64
     across
    0.64
    akei
    0.61
     peste
    0.61
     över
    0.60
    Activations Density 0.093%

    No Known Activations