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. 5-GEMMASCOPE-RES-16K
    6. 1422
    Prev
    Next
    INDEX
    Explanations

    titles and roles relating to law enforcement or legal positions

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 5-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_5/width_16k/average_l0_68
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.5.hook_resid_post
    Hook Layer
    5
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    skosten
    -0.78
    ⓘ
    -0.71
     Modi
    -0.71
    Modi
    -0.70
    FACTS
    -0.70
    UVWXYZ
    -0.68
    digm
    -0.68
    expandindo
    -0.67
    xFFFFFFFF
    -0.66
    Ulrich
    -0.65
    POSITIVE LOGITS
     deputy
    1.64
     Deputy
    1.59
     assistant
    1.58
     Assistant
    1.55
    Deputy
    1.52
    Assistant
    1.49
     ASSISTANT
    1.34
    PUTY
    1.34
    assistant
    1.33
     assistants
    1.00
    Activations Density 0.099%

    No Known Activations