© 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. 23-GEMMASCOPE-RES-16K
    6. 6718
    Prev
    Next
    INDEX
    Explanations

    terms and references related to influential architects and their designs

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    mentions of influential architects and their works

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     विश्वसनीयता
    -0.69
    mybatisplus
    -0.67
    tagext
    -0.64
    GOTREF
    -0.61
     ImportError
    -0.59
     XCTest
    -0.57
     дописавши
    -0.56
    DebuggerNonUser
    -0.55
     SwitchCompat
    -0.55
    Comedy
    -0.54
    POSITIVE LOGITS
     architecture
    1.57
     architects
    1.57
     architectural
    1.52
     architect
    1.51
     Architecture
    1.45
     Architect
    1.38
     Architects
    1.35
    architecture
    1.33
    Architecture
    1.32
    Architect
    1.28
    Activations Density 0.151%

    No Known Activations