Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 80647
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to architecture and architectural design

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

    architecture and architectural styles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B-IT @ 20-gemmascope-res-131k
    Configuration
    google/gemma-scope-9b-it-res/layer_20/width_131k/average_l0_81
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    131,072
    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
    Tikang
    -0.64
    posedge
    -0.59
    Joe
    -0.57
     Joe
    -0.53
     JOE
    -0.47
    Ryan
    -0.46
     Ryan
    -0.46
    mazan
    -0.45
    旦
    -0.44
     חיצוניים
    -0.44
    POSITIVE LOGITS
     architecture
    1.10
    architecture
    1.01
     Architecture
    1.01
     arquitect
    1.00
    Architecture
    1.00
     arquitectura
    0.98
    Architect
    0.96
     architectural
    0.96
     Architect
    0.96
     architect
    0.95
    Activations Density 0.007%

    No Known Activations