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
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 11553
    Prev
    Next
    INDEX
    Explanations

    structured data and its properties

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-9B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-9b-pt-res/layer_21/width_16k/average_l0_129
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "]);
    
    -0.50
    "]).
    -0.47
     resourceCulture
    -0.46
    )];
    
    -0.45
    '])->
    -0.45
    躇
    -0.45
     disambiguazione
    -0.45
    +#+
    -0.44
    ])){
    -0.44
     Core
    -0.44
    POSITIVE LOGITS
     apakah
    0.46
     Wicidata
    0.44
     digitais
    0.44
     Ahnung
    0.42
     whether
    0.40
     dodatkowe
    0.40
     postępo
    0.39
     Spuren
    0.39
    Litteratur
    0.39
    setcounter
    0.38
    Activations Density 0.574%

    No Known Activations