© 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. 25-GEMMASCOPE-RES-16K
    6. 12220
    Prev
    Next
    INDEX
    Explanations

    technical details related to electronic devices and their specifications

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 25-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_25/width_16k/average_l0_116
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.25.hook_resid_post
    Hook Layer
    25
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Devices
    -0.85
     Devices
    -0.85
     Sites
    -0.84
    Sites
    -0.82
    Variants
    -0.80
    Operators
    -0.80
     Companies
    -0.80
    Groups
    -0.79
     Players
    -0.79
    Companies
    -0.78
    POSITIVE LOGITS
     ones
    0.73
    BeginContext
    0.61
     AssemblyTitle
    0.51
     Profitez
    0.49
     wines
    0.48
     cards
    0.48
     tapes
    0.47
    ledu
    0.46
     stones
    0.46
     films
    0.46
    Activations Density 2.121%

    No Known Activations