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. 3-GEMMASCOPE-RES-16K
    6. 6274
    Prev
    Next
    INDEX
    Explanations

    terms related to the word "Bal" and its various forms in different contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Comparing With GEMMA-2-2B @ 3-gemmascope-res-16k
    Configuration
    google/gemma-scope-2b-pt-res/layer_3/width_16k/average_l0_59
    Prompts (Dashboard)
    36,864 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    16,384
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Hook Layer
    3
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Activation Function
    relu
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    >-->
    -0.79
    goku
    -0.75
    })]
    -0.74
    })));
    -0.73
     Brutus
    -0.71
     Biggs
    -0.71
     Buhari
    -0.70
     Sixt
    -0.69
     nahilalakip
    -0.68
    OGND
    -0.68
    POSITIVE LOGITS
     Bal
    3.35
    Bal
    3.22
     bal
    3.09
    bal
    2.80
     BAL
    2.63
    BAL
    2.53
     Бал
    1.63
     Balak
    1.59
     Balt
    1.58
     Balm
    1.54
    Activations Density 0.103%

    No Known Activations