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. 23-GEMMASCOPE-RES-16K
    6. 10461
    Prev
    Next
    INDEX
    Explanations

    phrases related to economic power dynamics and consumer behaviors

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 23-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_23/width_16k/average_l0_75
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Hook Layer
    23
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    mybatisplus
    -0.61
    GEBURTS
    -0.60
     mergeFrom
    -0.56
     Вікіпе
    -0.53
    MessageOf
    -0.52
    Parcelize
    -0.52
     InputDecoration
    -0.52
     saites
    -0.52
    gelopen
    -0.50
    __":
    
    -0.50
    POSITIVE LOGITS
     power
    3.92
    power
    3.48
    Power
    2.99
     Power
    2.96
     POWER
    2.82
    POWER
    2.81
     powers
    2.52
     puissance
    2.38
    powers
    2.35
     poder
    2.26
    Activations Density 0.590%

    No Known Activations