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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 692
    Prev
    Next
    INDEX
    Explanations

    numerical data and references to financial concepts

    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
     CreateTagHelper
    -0.66
    ]")]
    -0.59
     désolés
    -0.58
    Portale
    -0.58
     Reverso
    -0.57
    findpost
    -0.56
    enumi
    -0.55
     firmado
    -0.54
    ConstraintMaker
    -0.54
     Azt
    -0.54
    POSITIVE LOGITS
     مشين
    0.61
    ఔ
    0.55
     تانيه
    0.53
     nahilalakip
    0.52
     tarto
    0.51
    argout
    0.50
    NotFoundError
    0.50
    Zunanje
    0.49
    Šaltiniai
    0.49
     calme
    0.49
    Activations Density 0.697%

    No Known Activations