© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 24-GEMMASCOPE-RES-16K
    6. 13439
    Prev
    Next
    INDEX
    Explanations

    legal concepts related to judgment and rulings

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

    Non-English words, code snippets, and citations

    np_acts-logits-general · gemini-2.0-flash

    legal and code citations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 24-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_24/width_16k/average_l0_73
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.24.hook_resid_post
    Hook Layer
    24
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ed
    -0.53
    }]
    
    -0.53
    AnchorStyles
    -0.52
    EntityFramework
    -0.49
    ing
    -0.48
    ↵
    -0.47
    .")]
    -0.46
     تضيفلها
    -0.45
    Nazionale
    -0.44
    ign
    -0.43
    POSITIVE LOGITS
    にほんブログ村
    1.44
    -------
    1.09
    Inhalts
    0.61
    rungsseite
    0.61
    verwijspagina
    0.59
     Ganes
    0.59
     poveznice
    0.57
    /***/
    0.56
     Wikispecies
    0.56
    LabelTagHelper
    0.56
    Activations Density 0.047%

    No Known Activations