© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 9459
    Prev
    Next
    INDEX
    Explanations

    terms related to terminal devices and connections in technology and electronics

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Italijanski
    -0.67
     turística
    -0.62
    dafx
    -0.59
     Privy
    -0.59
     touristes
    -0.59
     turístico
    -0.57
    nursing
    -0.56
    uxxxx
    -0.56
     يتيمه
    -0.54
     policiers
    -0.54
    POSITIVE LOGITS
     terminal
    0.74
     diagonal
    0.71
     Terminal
    0.70
     terminals
    0.66
     battery
    0.64
     batteries
    0.64
    berger
    0.63
     batterie
    0.61
    terminal
    0.61
    viewDidLoad
    0.61
    Activations Density 0.089%

    No Known Activations