© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    5. Gemma-2-2B
    7. Residual Stream - 16k
    9. 3-GEMMASCOPE-RES-16K
    11. 12201
    Prev
    Next
    INDEX
    Explanations

    phrases that discuss potential outcomes or opportunities

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kereszt
    -0.65
     zdra
    -0.64
     Floren
    -0.62
    közi
    -0.61
     cuantas
    -0.60
    Eqn
    -0.59
    Verts
    -0.58
     адресу
    -0.56
    валь
    -0.56
    Dziękuję
    -0.55
    POSITIVE LOGITS
     possibility
    2.85
     Possibility
    2.56
    possibility
    2.48
     possibilities
    2.40
    Possibility
    2.20
     Possibilities
    2.13
     posibilidad
    1.83
     possibilidade
    1.80
     possib
    1.74
     possibilité
    1.70
    Activations Density 0.089%

    No Known Activations