Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 0-GEMMASCOPE-RES-16K
    6. 7997
    Prev
    Next
    INDEX
    Explanations

    mentions of different types of media and their influences

    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
     Diſ
    -1.11
     itſelf
    -1.06
     houſe
    -1.04
     Houſe
    -1.03
    mybatisplus
    -1.02
     faſt
    -1.01
     Eſ
    -1.01
     myſelf
    -1.00
     whoſe
    -0.99
     themſelves
    -0.98
    POSITIVE LOGITS
     Media
    1.01
     media
    0.92
    medi
    0.77
    Media
    0.76
    media
    0.76
     MEDIA
    0.70
     Med
    0.67
     med
    0.64
     top
    0.60
     leaf
    0.60
    Activations Density 0.090%

    No Known Activations