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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & 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. 2-GEMMASCOPE-RES-16K
    6. 4669
    Prev
    Next
    INDEX
    Explanations

    numbered references or citations in a statistical context

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 2-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_2/width_16k/average_l0_141
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.2.hook_resid_post
    Hook Layer
    2
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     still
    -0.55
    معلومات
    -0.55
     baby
    -0.51
     stil
    -0.50
     voyons
    -0.48
    TypedDataSet
    -0.48
    üng
    -0.48
     litté
    -0.47
    Coordonnées
    -0.46
    Stil
    -0.46
    POSITIVE LOGITS
     ""],
    0.77
    ."),
    0.70
    ItemBackground
    0.68
     >=",
    0.66
    atories
    0.64
    #
    0.63
    ainville
    0.63
    LoS
    0.61
    — 
    0.60
    ngdoc
    0.60
    Activations Density 0.298%

    No Known Activations