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. 7-GEMMASCOPE-RES-16K
    6. 6123
    Prev
    Next
    INDEX
    Explanations

    phrases denoting potential and possibility in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 7-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_7/width_16k/average_l0_69
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Hook Layer
    7
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Burrow
    -0.66
     Biscuits
    -0.66
    rhosis
    -0.61
     Chy
    -0.58
     escuchadas
    -0.58
     Biscuit
    -0.57
     hands
    -0.57
     Zer
    -0.57
     HANDS
    -0.56
     edi
    -0.56
    POSITIVE LOGITS
     potential
    2.00
     Potential
    1.94
    Potential
    1.93
    potential
    1.80
     POTENTIAL
    1.72
     potentials
    1.56
     potencial
    1.51
     potenciales
    1.45
     potensi
    1.43
     потенциаль
    1.38
    Activations Density 0.142%

    No Known Activations