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. 21-GEMMASCOPE-RES-16K
    6. 415
    Prev
    Next
    INDEX
    Explanations

    legal terms and references related to court cases and judgments

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Personensuche
    -1.34
    DockStyle
    -1.06
    bootstrapcdn
    -1.05
     wireType
    -1.02
    principalColumn
    -0.99
    expandindo
    -0.99
    WriteBarrier
    -0.97
     themſelves
    -0.97
    KURZBESCHREIBUNG
    -0.95
     itſelf
    -0.94
    POSITIVE LOGITS
     la
    0.54
     l
    0.53
     những
    0.51
     una
    0.47
     un
    0.47
     την
    0.42
     τον
    0.41
     ceux
    0.37
     el
    0.35
     
    0.33
    Activations Density 0.046%

    No Known Activations