© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Google DeepMind · Exploring Gemma 2 with Gemma Scope
    3. Gemma-2-2B
    4. Residual Stream - 16k
    5. 21-GEMMASCOPE-RES-16K
    6. 13192
    Prev
    Next
    INDEX
    Explanations

    instances of the word "some" or variations indicating quantity or group

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 21-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_21/width_16k/average_l0_70
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Hook Layer
    21
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     respectivas
    -0.54
     respectivos
    -0.53
     respectively
    -0.52
     jeweiligen
    -0.48
     illetve
    -0.46
     összes
    -0.46
    分别
    -0.45
    ものである
    -0.44
    }*/
    
    -0.44
     distintas
    -0.44
    POSITIVE LOGITS
     people
    1.45
     folks
    1.02
    people
    1.00
    Portale
    0.96
     commentators
    0.88
     experts
    0.88
     jurisdictions
    0.88
     countries
    0.87
     Americans
    0.87
     studies
    0.86
    Activations Density 0.246%

    No Known Activations