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. 2-GEMMASCOPE-RES-16K
    6. 6218
    Prev
    Next
    INDEX
    Explanations

    terms related to specifications and standards

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    HomeAsUp
    -0.70
     Stoner
    -0.66
     virke
    -0.64
     contextLoads
    -0.64
    ReadByte
    -0.64
     Mero
    -0.63
     հղումներ
    -0.63
     trier
    -0.63
    קישורים
    -0.61
     noDo
    -0.61
    POSITIVE LOGITS
     specifications
    2.95
     specification
    2.92
     Specification
    2.76
     Specifications
    2.70
     specs
    2.56
    specification
    2.50
    Specification
    2.42
    specifications
    2.39
    Specifications
    2.37
     Specs
    2.30
    Activations Density 0.067%

    No Known Activations