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-2-9B-IT
    4. Residual Stream - 131k
    5. 20-GEMMASCOPE-RES-131K
    6. 72716
    Prev
    Next
    INDEX
    Explanations

    headings and sections related to methodology in research papers

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
     kasarigan
    -0.51
     snippetHide
    -0.47
    UVWXYZ
    -0.47
    #+#
    -0.46
     pinulongan
    -0.43
    󠁬
    -0.43
    HomeAsUpEnabled
    -0.43
    WriteAttribute
    -0.41
     चीज़ों
    -0.41
    ChromeDriver
    -0.40
    POSITIVE LOGITS
    Autowired
    0.41
    UKAN
    0.40
    JoinColumn
    0.40
     Roskov
    0.40
    ToUse
    0.40
    ştır
    0.40
     Competence
    0.39
     Czer
    0.39
     Intent
    0.38
     Bersama
    0.38
    Activations Density 0.028%

    No Known Activations