© 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
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 5-GEMMASCOPE-RES-16K
    6. 8445
    Prev
    Next
    INDEX
    Explanations

    references to dual or multiple functionalities or characteristics

    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
     PRD
    -0.93
     financeira
    -0.90
     CRI
    -0.88
     IMP
    -0.88
     Rasa
    -0.81
     مشين
    -0.81
     HasFactory
    -0.81
    Portale
    -0.81
    ErrorListener
    -0.79
    ніципалі
    -0.79
    POSITIVE LOGITS
     dual
    1.84
     Dual
    1.77
     DUAL
    1.72
    Dual
    1.62
    dual
    1.52
     twin
    1.32
     du
    1.27
     Du
    1.21
     duel
    1.18
     Duel
    1.15
    Activations Density 0.098%

    No Known Activations