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. 16-GEMMASCOPE-RES-16K
    6. 12904
    Prev
    Next
    INDEX
    Explanations

    discussions of elite social structures and their impact on society

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

    "origin"

    np_acts-logits-general · gemini-2.0-flash

    origin or cause

    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
     Aim
    -0.44
    Aim
    -0.44
     aiming
    -0.42
     chaleco
    -0.41
    aba
    -0.40
     Nicholson
    -0.39
     لدى
    -0.38
     пока
    -0.37
    umani
    -0.36
     تجاه
    -0.36
    POSITIVE LOGITS
     origin
    1.21
     origins
    1.21
     origen
    1.10
    origin
    1.07
    Origin
    1.07
     Origin
    1.03
    origen
    1.02
     originate
    1.01
     ORIGIN
    0.98
     originating
    0.95
    Activations Density 0.828%

    No Known Activations