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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 1-GEMMASCOPE-RES-16K
    6. 8018
    Prev
    Next
    INDEX
    Explanations

    the name "Zaza" or variations of it appearing in multiple contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 1-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_1/width_16k/average_l0_102
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.1.hook_resid_post
    Hook Layer
    1
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     giù
    -0.61
    ())).
    -0.54
     morire
    -0.53
     geografia
    -0.51
     elettron
    -0.51
     scienza
    -0.50
    Demografía
    -0.50
    }">
    -0.49
    ())));
    -0.49
    Tobias
    -0.49
    POSITIVE LOGITS
     vor
    1.15
     Vor
    0.97
    za
    0.82
    Portale
    0.81
     виправивши
    0.80
    Vor
    0.80
    ZA
    0.76
    存于互联网档案馆
    0.75
    amsa
    0.73
     Mah
    0.72
    Activations Density 0.039%

    No Known Activations