© 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. 8468
    Prev
    Next
    INDEX
    Explanations

    references to design concepts and processes

    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
    design
    -1.27
     design
    -1.18
    Design
    -1.11
     Design
    -1.08
     DESIGN
    -1.06
    DESIGN
    -1.01
     diseño
    -0.94
     designs
    -0.93
     desain
    -0.92
     designer
    -0.91
    POSITIVE LOGITS
     Thinking
    0.69
     '\\;'
    0.67
    ator
    0.66
    ators
    0.64
    aarrggbb
    0.63
     thinking
    0.60
     elements
    0.57
     ногтей
    0.57
     flaw
    0.57
    ate
    0.55
    Activations Density 0.159%

    No Known Activations