© 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-2-9B
    4. Residual Stream - 16k
    5. 20-GEMMASCOPE-RES-16K
    6. 9745
    Prev
    Next
    INDEX
    Explanations

    terms related to bonds and connectivity in graph theory and lattice structures

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

    terminology related to bonds and connections in mathematical network or graph theory.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_20/width_16k/average_l0_68
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     queſta
    -0.66
    UrlResolution
    -0.65
     EconPapers
    -0.65
    ロウィン
    -0.63
    MemoryWarning
    -0.63
     pinulongan
    -0.62
     ModelRenderer
    -0.61
     utafitiHapana
    -0.60
     viewDidLoad
    -0.60
    Portail
    -0.59
    POSITIVE LOGITS
     between
    0.79
     между
    0.62
     Between
    0.61
     zwischen
    0.59
    Between
    0.59
    between
    0.58
     między
    0.55
     між
    0.54
     inter
    0.53
     mezi
    0.51
    Activations Density 1.089%

    No Known Activations