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. 29549
    Prev
    Next
    INDEX
    Explanations

    references to specific locations and terms related to gastric cancer

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

    Jakarta, gastric cancer

    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
    enumi
    -0.53
    neuf
    -0.48
    op
    -0.48
    spf
    -0.45
    いれば
    -0.43
     naman
    -0.42
    LEEP
    -0.42
    ϕ
    -0.41
    vänd
    -0.41
    off
    -0.41
    POSITIVE LOGITS
     ISNI
    1.16
    Jakarta
    1.15
     Jakarta
    1.12
    JAKARTA
    1.08
     jakarta
    1.08
    jakarta
    0.81
     defaultstate
    0.63
     JAKARTA
    0.63
    flashdata
    0.63
    ChromeDriver
    0.56
    Activations Density 0.003%

    No Known Activations