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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 4-GEMMASCOPE-RES-16K
    6. 11067
    Prev
    Next
    INDEX
    Explanations

    references to risk assessment and its evaluation in environmental or health contexts

    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
    PostBack
    -0.85
     nakalista
    -0.84
     Tade
    -0.83
    PMailer
    -0.74
     సౌకర్య
    -0.72
     Waray
    -0.71
     indietro
    -0.71
     Waldo
    -0.71
    GEBURTSDATUM
    -0.70
     Trey
    -0.70
    POSITIVE LOGITS
    澈
    0.59
    ColumnInfo
    0.55
     Chin
    0.55
     rotina
    0.54
    كويكب
    0.53
    renden
    0.53
    ClientSize
    0.51
    Eure
    0.49
    rfloor
    0.49
    QUIRY
    0.49
    Activations Density 0.449%

    No Known Activations