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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsBlogSlackPrivacy & 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. 20-GEMMASCOPE-RES-16K
    6. 30
    Prev
    Next
    INDEX
    Explanations

    terms and references associated with political and social organizations

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 20-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_20/width_16k/average_l0_71
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.20.hook_resid_post
    Hook Layer
    20
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     femininas
    -0.58
     hombros
    -0.56
     démocr
    -0.55
     möjligt
    -0.52
    ParallelGroup
    -0.51
    vábbi
    -0.49
     illustrationer
    -0.49
     consultato
    -0.47
     řízení
    -0.47
     sanitaires
    -0.47
    POSITIVE LOGITS
     enthusiasts
    1.21
     users
    1.16
     dwellers
    1.13
     participants
    1.12
     specialists
    1.10
     lovers
    1.07
     professionals
    1.06
     workers
    1.06
    ists
    1.05
     seekers
    1.04
    Activations Density 0.876%

    No Known Activations