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. 44114
    Prev
    Next
    INDEX
    Explanations

    the presence of structured references or elements related to a dashboard in web applications

    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
     <=",
    -0.91
     Италијани
    -0.73
    GIVEREF
    -0.69
     Chwiliwch
    -0.68
     CreateTagHelper
    -0.65
     المعيارى
    -0.65
    aarrggbb
    -0.64
     propOrder
    -0.64
    )');
    -0.64
    ]")]
    -0.63
    POSITIVE LOGITS
     nocturna
    0.39
     fédé
    0.35
     âmes
    0.33
     juges
    0.32
     respectivos
    0.30
     telefónica
    0.29
     auriculares
    0.29
     réserv
    0.29
    กาย
    0.28
     masculina
    0.28
    Activations Density 0.000%

    No Known Activations