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. 16-GEMMASCOPE-RES-16K
    6. 9114
    Prev
    Next
    INDEX
    Explanations

    indications of cause and effect relationships

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Follows coordinating conjunctions and pronouns

    np_acts-logits-general · gemini-2.0-flash

    viruses, argument, Dudarova

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 16-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_16/width_16k/average_l0_78
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.16.hook_resid_post
    Hook Layer
    16
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ſelves
    -0.63
     myſelf
    -0.62
    ſelf
    -0.55
     greateſt
    -0.51
    seamnă
    -0.51
    dillas
    -0.50
     AppColors
    -0.49
     ſy
    -0.49
     Confira
    -0.49
    Есть
    -0.48
    POSITIVE LOGITS
     he
    0.94
     they
    0.86
    Datuak
    0.79
     He
    0.72
     tartalomajánló
    0.71
     הוא
    0.68
     он
    0.67
     she
    0.65
    He
    0.61
     они
    0.59
    Activations Density 0.442%

    No Known Activations