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. 0-GEMMASCOPE-RES-16K
    6. 7082
    Prev
    Next
    INDEX
    Explanations

    references to specific complex terms or concepts, particularly in relation to coal and environmental contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 0-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_0/width_16k/average_l0_105
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.0.hook_resid_post
    Hook Layer
    0
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     negroes
    -0.85
     sherds
    -0.81
     Cæsar
    -0.80
    PreferredItem
    -0.79
    الحياه
    -0.78
    AntiForgeryToken
    -0.78
     Negroes
    -0.78
     Pliny
    -0.77
     Lilith
    -0.77
    Становништво
    -0.77
    POSITIVE LOGITS
     sophisticated
    0.67
    ree
    0.65
    ota
    0.64
     Antonio
    0.61
    ying
    0.60
     compound
    0.58
    clo
    0.53
     Mason
    0.53
     von
    0.52
     modal
    0.52
    Activations Density 0.098%

    No Known Activations