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. 4-GEMMASCOPE-RES-16K
    6. 11134
    Prev
    Next
    INDEX
    Explanations

    words associated with legal terms and processes

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 4-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_4/width_16k/average_l0_124
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.4.hook_resid_post
    Hook Layer
    4
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     kasarigan
    -0.59
    RegistryLite
    -0.58
    oa̍t
    -0.57
     кӀ
    -0.57
     linkovi
    -0.56
    exitRule
    -0.51
     ligiloj
    -0.50
    endgroup
    -0.50
    ⓧ
    -0.49
    تقاوى
    -0.49
    POSITIVE LOGITS
     Biden
    0.66
    AlterField
    0.64
     Obama
    0.60
    PreferredItem
    0.59
    AxisAlignment
    0.59
     []:
    0.58
    SQLiteDatabase
    0.58
    CodeAnalysis
    0.57
    Biden
    0.57
    kloped
    0.55
    Activations Density 1.728%

    No Known Activations