Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsBlogSlackPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 7388
    Prev
    Next
    INDEX
    Explanations

    elements of a programming language, particularly related to data structures and error handling

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    __);
    -0.68
    {{/
    -0.66
    NonNull
    -0.66
    SuccessListener
    -0.65
    synthesize
    -0.64
     BioLib
    -0.64
    gency
    -0.64
    μβρίου
    -0.62
    ("$.
    -0.62
    ViewInit
    -0.62
    POSITIVE LOGITS
    TagMode
    0.63
     nahilalakip
    0.57
     Aper
    0.50
     deme
    0.47
     pho
    0.45
    featureID
    0.45
    esgue
    0.45
    RetentionPolicy
    0.44
     voulais
    0.44
    CLING
    0.43
    Activations Density 0.115%

    No Known Activations